Emotion-associated representations in the feed forward gates of a language model

Identifying emotion-associated neurons in large language models does not establish how those neurons contribute to emotional behavior. This study investigates that distinction through three levels of explanation: representation, reconfiguration, and causal control. Statistically corrected feed-forward activation signatures in Qwen2.5-1.5B-Instruct exhibited structured overlap corresponding to a psychological circumplex model, with substantial but incomplete reproducibility across Chinese texts and their English translations. Four experimental task families investigated whether these signatures changed with behavioral demands and predicted model outputs. The preregistered internal measure failed held-out validation, with only two of fourteen hypotheses supported; post hoc corrected measures revealed task-dependent reconfiguration and several associations with behavioral measures. However, increased internal separation did not consistently improve discrimination accuracy, evidence-specific changes depended on the internal measure, and static neuronal overlap did not predict generated-text confusability under the designated classifier, although a secondary lexicon analysis showed the predicted association. Suppression of emotional expression was not accompanied by a reliably detected change at the sampled pre-generation position. These findings demonstrate that emotion-associated activation structure and task responsiveness do not, by themselves, provide a general explanation of emotional behavior. The study establishes the need to distinguish representational association, task-dependent reconfiguration, and causal control, the last of which remains untested.

Authors

Institutions

Publication Details

Journal
Journal of High School Science
Published
2026-11-20
DOI
https://doi.org/10.64336/001c.175619
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Emotion-associated representations in the feed forward gates of a language model

Sankar Balasubramanian, Rayan Upadhyay
2 links
Journal of High School Science
Explainable Artificial Intelligence (XAI)
article

Emotion-associated representations in the feed forward gates of a language model

Sankar Balasubramanian, Rayan Upadhyay
article en

Abstract

Identifying emotion-associated neurons in large language models does not establish how those neurons contribute to emotional behavior. This study investigates that distinction through three levels of explanation: representation, reconfiguration, and causal control. Statistically corrected feed-forward activation signatures in Qwen2.5-1.5B-Instruct exhibited structured overlap corresponding to a psychological circumplex model, with substantial but incomplete reproducibility across Chinese texts and their English translations. Four experimental task families investigated whether these signatures changed with behavioral demands and predicted model outputs. The preregistered internal measure failed held-out validation, with only two of fourteen hypotheses supported; post hoc corrected measures revealed task-dependent reconfiguration and several associations with behavioral measures. However, increased internal separation did not consistently improve discrimination accuracy, evidence-specific changes depended on the internal measure, and static neuronal overlap did not predict generated-text confusability under the designated classifier, although a secondary lexicon analysis showed the predicted association. Suppression of emotional expression was not accompanied by a reliably detected change at the sampled pre-generation position. These findings demonstrate that emotion-associated activation structure and task responsiveness do not, by themselves, provide a general explanation of emotional behavior. The study establishes the need to distinguish representational association, task-dependent reconfiguration, and causal control, the last of which remains untested.

Journal of High School ScienceVol. 10(4)
Indian Institute of Science Bangalore (IN)
Explainable Artificial Intelligence (XAI)
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Emotion-associated representations in the feed forward gates of a language model — Sankar Balasubramanian, Rayan Upadhyay · Journal of High School Science (2026) | TGRS Research Map | TGRS