The Inner Sentiments of a Thought

TL;DR

This paper investigates how large language models implicitly encode and can be used to analyze and generate sentences with specific sentiments, revealing insights into their internal emotional representations.

Contribution

It introduces methods to predict and analyze sentiment distributions within LLMs, providing new tools for understanding and manipulating the model's emotional content.

Findings

Predictors of sentiment distributions are well calibrated.

Sentiment predictors can analyze how conjunctions affect emotional tone.

Distributional predictions enable generation of sentences with extreme sentiments.

Abstract

Transformer-based large-scale language models (LLMs) are able to generate highly realistic text. They are duly able to express, and at least implicitly represent, a wide range of sentiments and color, from the obvious, such as valence and arousal to the subtle, such as determination and admiration. We provide a first exploration of these representations and how they can be used for understanding the inner sentimental workings of single sentences. We train predictors of the quantiles of the distributions of final sentiments of sentences from the hidden representations of an LLM applied to prefixes of increasing lengths. After showing that predictors of distributions of valence, determination, admiration, anxiety and annoyance are well calibrated, we provide examples of using these predictors for analyzing sentences, illustrating, for instance, how even ordinary conjunctions (e.g., "but") can dramatically alter the emotional trajectory of an utterance. We then show how to exploit the distributional predictions to generate sentences with sentiments in the tails of distributions. We discuss the implications of our results for the inner workings of thoughts, for instance for psychiatric dysfunction.