# Towards Label-Agnostic Emotion Embeddings

arXiv: https://arxiv.org/abs/2012.00190 · HTML: https://mlsanity.com/paper/2012.00190/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [Dimensional Modeling of Emotions in Text with Appraisal Theories: Corpus Creation, Annotation Reliability, and Prediction](https://mlsanity.com/paper/2206.05238/) (2022)
- [Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Models](https://mlsanity.com/paper/2510.22042/) (2025)
- [Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora](https://mlsanity.com/paper/2209.06701/) (2022)
- [StockEmotions: Discover Investor Emotions for Financial Sentiment Analysis and Multivariate Time Series](https://mlsanity.com/paper/2301.09279/) (2023)
- [Where are We in Event-centric Emotion Analysis? Bridging Emotion Role Labeling and Appraisal-based Approaches](https://mlsanity.com/paper/2309.02092/) (2023)
- [Improving Language Models for Emotion Analysis: Insights from Cognitive Science](https://mlsanity.com/paper/2406.10265/) (2024)
- [Contrastive Distillation of Emotion Knowledge from LLMs for Zero-Shot Emotion Recognition](https://mlsanity.com/paper/2505.18040/) (2025)
- [CEI: A Benchmark for Evaluating Pragmatic Reasoning in Language Models](https://mlsanity.com/paper/2603.09993/) (2026)
- [A Comparative Study on Affective Cues in Text Embeddings Across Psychological Emotion Theories](https://mlsanity.com/paper/2606.29068/) (2026)

## Abstract (arXiv)

Research in emotion analysis is scattered across different label formats (e.g., polarity types, basic emotion categories, and affective dimensions), linguistic levels (word vs. sentence vs. discourse), and, of course, (few well-resourced but much more under-resourced) natural languages and text genres (e.g., product reviews, tweets, news). The resulting heterogeneity makes data and software developed under these conflicting constraints hard to compare and challenging to integrate. To resolve this unsatisfactory state of affairs we here propose a training scheme that learns a shared latent representation of emotion independent from different label formats, natural languages, and even disparate model architectures. Experiments on a wide range of datasets indicate that this approach yields the desired interoperability without penalizing prediction quality. Code and data are archived under DOI 10.5281/zenodo.5466068.