Related papers: Shared Emotion Geometry Across Small Language Mode…
Small language models (SLMs) in the 100M-10B parameter range increasingly power production systems, yet whether they possess the internal emotion representations recently discovered in frontier models remains unknown. We present the first…
We characterize a compositional architecture of literary primitives in two instruction-tuned large language models (Llama 3.1 8B-Instruct and Gemma 2 9B-IT) via sparse autoencoders on mid-depth residual streams. Four feature classes emerge:…
This work investigates how large language models (LLMs) internally represent emotion by analyzing the geometry of their hidden-state space. The paper identifies a low-dimensional emotional manifold and shows that emotional representations…
Large Language Models (LLMs) are increasingly expected to navigate the nuances of human emotion. While research confirms that LLMs can simulate emotional intelligence, their internal emotional mechanisms remain largely unexplored. This…
Human emotions are often not expressed directly, but regulated according to internal processes and social display rules. For affective computing systems, an understanding of how users regulate their emotions can be highly useful, for…
The geometric structure of latent representations in large language models (LLMs) is an active area of research, driven in part by its implications for model transparency and AI safety. Existing literature has focused mainly on general…
Why do language models from different architecture families respond so differently to the same perturbation? We argue that the answer is not scale, but \emph{how architecture shapes information compression}. Analyzing eight Transformer…
Large language models can generate responses that resemble emotional distress, and this raises concerns around model reliability and safety. We introduce a set of evaluations to investigate expressions of distress in LLMs, and find that…
Emotion recognition has become an important research topic in the field of human-computer interaction. Studies on sound and videos to understand emotions focused mainly on analyzing facial expressions and classified 6 basic emotions. In…
In this work, we conduct an analysis to examine the consistency of Large Language Models (LLMs) with respect to their own generated responses in an emotionally-driven conversational context. Specifically, the text generated by LLM is framed…
Vision-language models encode continuous geometry that their text pathway fails to express: a 6,000-parameter linear probe extracts hand joint angles at 6.1 degrees MAE from frozen features, while the best text output achieves only 20.0…
Accurate emotion perception is crucial for various applications, including human-computer interaction, education, and counseling. However, traditional single-modality approaches often fail to capture the complexity of real-world emotional…
Human annotators frequently disagree on emotion labels, yet most evaluations of Large Language Model (LLM) emotion annotation collapse these judgments into a single gold standard, discarding the distributional information that disagreement…
We propose Curved Inference - a geometric Interpretability framework that tracks how the residual stream trajectory of a large language model bends in response to shifts in semantic concern. Across 20 matched prompts spanning emotional,…
While Large Language Models (LLMs) demonstrate increasingly sophisticated affective capabilities, the internal mechanisms by which they process complex emotions remain unclear. Existing interpretability approaches often treat models as…
How do transformer language models represent magnitude? Recent work disagrees: some find logarithmic spacing, others linear encoding, others per-digit circular representations. We apply the formal tools of psychophysics to resolve this.…
We show that emotion vectors in LLMs are organized by a two-dimensional valence-arousal (VA) subspace exhibiting circular geometry. Through principal component decomposition and ridge regression, we recover meaningful VA axes underlying…
Large Language Models (LLMs) have rapidly become central to NLP, demonstrating their ability to adapt to various tasks through prompting techniques, including sentiment analysis. However, we still have a limited understanding of how these…
As large language models (LLMs) become increasingly integrated into robotic systems, their potential to generate socially and culturally appropriate affective touch remains largely unexplored. This study investigates whether…
Large Language Models (LLMs) frequently prioritize conflicting in-context information over pre-existing parametric memory, a phenomenon often termed sycophancy or compliance. However, the mechanistic realization of this behavior remains…