Skip to content
AI News HubLIVE
Original source2 min read

Interpretable Symptom Vectors for Depression in a Large Language Model

Summary

A study applies mechanistic interpretability to Gemma-3-27B-PT's residual stream, finding that symptom groups separate geometrically at layer 21 and that symptom vectors projected from naturalistic text preserve clinician-annotated ordering, offering a mechanistic basis for interpretable depression assessment.

SourcearXiv Computational LinguisticsAuthor: Fangyi Zhu, Ajay Subramanian, Allison Constant, Camille Wang, Ravish Gupta, Corey J. Keller
Interpretable Symptom Vectors for Depression in a Large Language Model
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 1 Sep 2026]

Title:Interpretable Symptom Vectors for Depression in a Large Language Model

View a PDF of the paper titled Interpretable Symptom Vectors for Depression in a Large Language Model, by Fangyi Zhu and 5 other authors

View PDF HTML (experimental)

Abstract:Patients with depression present with diverse symptom profiles, yet clinical practice routinely reduces this variation to a single severity score. Large language models (LLMs) can potentially capture various symptoms and their severity from patient speech. However, how depressive symptoms are represented inside LLMs remains poorly understood, limiting clinical trust. To examine whether internal model activations match clinician judgment, we analyzed the residual stream of Gemma-3-27B-PT using mechanistic interpretability techniques. Recording activations across symptom descriptions drawn from validated clinical instruments, we found that symptom groups geometrically separated the most at layer 21 across multiple distance metrics. Using Semantic Projection, we then projected held-out naturalistic text onto Symptom Vectors constructed from these instruments. The resulting per-symptom coefficients preserved clinician-annotated rank ordering across mood, somatic, and suicidality axes. Furthermore, a single depression vector in Layer 21 separates held-out depressive from non-depressive text (AUC = 0.789), which can be used as an emotional valence gate that restricts symptom projection to depressive speech. These results reveal a decorrelated, clinician-aligned symptom signal readable directly from internal activations, offering a mechanistic foundation for interpretable depression-assessment tools.

Comments: 26 pages, 6 figures

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC)

ACM classes: I.2.7; J.3

Cite as: arXiv:2609.01832 [cs.CL]

(or arXiv:2609.01832v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.01832

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Ravish Gupta [view email] [v1] Tue, 1 Sep 2026 20:07:03 UTC (448 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Interpretable Symptom Vectors for Depression in a Large Language Model, by Fangyi Zhu and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-09

Change to browse by:

cs cs.AI cs.LG q-bio q-bio.NC

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Analysis of Gemma-3-27B-PT's residual stream found symptom groups separated most at layer 21 across multiple distance metrics.
  • Semantic Projection of held-out naturalistic text onto symptom vectors preserved clinician-annotated rank ordering across mood, somatic, and suicidality axes.
  • A single depression vector at layer 21 distinguished depressive from non-depressive text with AUC = 0.789 and can act as an emotional valence gate.
  • The results reveal a decorrelated, clinician-aligned symptom signal readable from internal activations for interpretable depression-assessment tools.

Highlights and analysis are generated automatically and may contain errors. Check the original source.