Therapeutic Functions in Large Language Model Responses to Emotional Disclosures: Qualitative Content Analysis
JMIR Formative Research · 30.10.2026 · 10 · e104513-e104513
DOI: 10.2196/104513 ↗Kurz gefasst
Fachartikel in der Zeitschrift JMIR Formative Research, online erschienen am 30.10.2026. Verfasst von Haruka Notsu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Division of Digital Psychiatry, Department of Psychiatry, Beth Israel Deaconess Medical Center, 330 Brookline Avenue, Boston, MA, 02215, United State…. Hauptthemen laut MEDLINE: Large Language Models, Emotions. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Millions of people now use general-purpose large language models (LLMs) for mental health support, yet how these models respond to emotional disclosures and whether their responses functionally resemble established therapeutic practices remain uncharacterized.
Objective
This study aimed to characterize how frontier LLMs respond to emotionally charged messages and examine whether their response patterns resemble therapeutic practices associated with self-awareness.
Methods
We generated 54 simulated user inputs representing mild-to-moderate everyday emotional difficulties. These simulated user inputs were generated using 3 LLMs (GPT-5.5, Claude Opus 4.7, and Gemini 2.5 Pro). The simulated user inputs systematically varied across 3 lengths and 5 communicative registers, ranging from raw venting to pragmatic requests. Then, each simulated user input was presented as a standalone user turn to the same 3 frontier LLMs, yielding 162 responses. Two independent clinical coders qualitatively coded the resulting responses using an inductive approach.
Results
The codes were compared and consolidated through iterative consensus, which yielded 8 higher-order categories. Acknowledging and validating segments appeared in 89.5% (145/162) of responses, emotion-focused suggestions in 84.6% (137/162), and interpretation in 67.3% (109/162). These patterns converged on emotional self-awareness, a construct associated with adaptive emotion regulation, suggesting that LLMs may repeatedly enact a recognizable micro-process of validation, affect labeling, interpretation, reflection, and regulation support. Models differed in stance, with some assigning emotional labels and interpretations directly rather than prompting users’ own reflection.
Conclusions
Frontier LLMs respond to emotional disclosures in patterned, largely convergent ways that approximate therapeutic techniques for building emotional awareness, though delivered more didactically than in clinical practice. Whether these responses build genuine self-awareness, reduce symptoms, or provide therapeutic benefit requires controlled and naturalistic investigation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Digital Psychiatry, Department of Psychiatry, Beth Israel Deaconess Medical Center, 330 Brookline Avenue, Boston, MA, 02215, United States, 1-617-667-6700.
Zitieren
APA
Notsu, H., Ryan, S., Nguyen, P. A., Noorily, J., Flathers, M., & Torous, J. (2026). Therapeutic Functions in Large Language Model Responses to Emotional Disclosures: Qualitative Content Analysis. JMIR Formative Research, 10, e104513-e104513. https://doi.org/10.2196/104513
Vancouver
Notsu H, Ryan S, Nguyen PA, Noorily J, Flathers M, Torous J. Therapeutic Functions in Large Language Model Responses to Emotional Disclosures: Qualitative Content Analysis. JMIR Formative Research. 2026;10:e104513-e104513. doi:10.2196/104513
BibTeX
@article{Notsu2026,
author = {Notsu, Haruka and Ryan, Sean and Nguyen, Phuong Anh and Noorily, Jill and Flathers, Matthew and Torous, John},
title = {Therapeutic Functions in Large Language Model Responses to Emotional Disclosures: Qualitative Content Analysis},
journal = {JMIR Formative Research},
year = {2026},
volume = {10},
pages = {e104513--e104513},
doi = {10.2196/104513}
}
EUVIMED