The Echo Amplifies the Knowledge: Somatic Marker Analogues in Language Models via Emotion Vector Re-Injection
Jared Glover

TL;DR
This paper introduces a method to inject emotion-like features into language models, enhancing decision-making by simulating emotional memory, thus bridging the gap between knowledge and feeling.
Contribution
It demonstrates a novel approach to re-inject emotion vectors into language models, improving their decision-making capabilities in a psychologically valid manner.
Findings
Emotion echo steepens threat-safety gradient.
Emotion echo combined with semantic knowledge increases good decision rate to 80%.
Emotion echo alone does not significantly influence decisions.
Abstract
Current language model memory systems store what happened but not how it felt. This distinction -- between semantic memory (knowing about a past event) and episodic memory (re-experiencing it) -- was identified by Tulving as the difference between noetic and autonoetic consciousness. Damasio demonstrated that humans with intact knowledge but absent emotional markers exhibit impaired decision-making. We bridge this gap for language models. Using Gemma 3 1B-IT with pretrained Gemma Scope 2 sparse autoencoders, we identify 310 emotion-exclusive features at layer 22 with psychologically valid geometry. We construct distinctive-feature emotion vectors during experience and partially re-inject them during recall, triggered by context similarity at layer 7. We test four conditions paralleling Damasio's framework: A (no memory), B (semantic labels), C (emotion echo), and BC (semantic +…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
