# Is Sentiment Banana-Shaped? Exploring the Geometry and Portability of Sentiment Concept Vectors

arXiv: https://arxiv.org/abs/2601.07995 · HTML: https://mlsanity.com/paper/2601.07995/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Builds on (most cited first, 9 of 9)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Implicit Representations of Meaning in Neural Language Models](https://mlsanity.com/paper/2106.00737/) (2021)
- [EmbeddingGemma: Powerful and Lightweight Text Representations](https://mlsanity.com/paper/2509.20354/) (2025)
- [XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond](https://mlsanity.com/paper/2104.12250/) (2021)
- [EmoBank: Studying the Impact of Annotation Perspective and Representation Format on Dimensional Emotion Analysis](https://mlsanity.com/paper/2205.01996/) (2022)
- [The emotional arcs of stories are dominated by six basic shapes](https://mlsanity.com/paper/1606.07772/) (2016)
- [Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution](https://mlsanity.com/paper/2410.00153/) (2024)
- [The Emotion Dynamics of Literary Novels](https://mlsanity.com/paper/2403.02474/) (2024)

## Abstract (arXiv)

Use cases of sentiment analysis in the humanities often require contextualized, continuous scores. Concept Vector Projections (CVP) offer a recent solution: by modeling sentiment as a direction in embedding space, they produce continuous, multilingual scores that align closely with human judgments. Yet the method's portability across domains and underlying assumptions remain underexplored. We evaluate CVP across genres, historical periods, languages, and affective dimensions, finding that concept vectors trained on one corpus transfer well to others with minimal performance loss. To understand the patterns of generalization, we further examine the linearity assumption underlying CVP. Our findings suggest that while CVP is a portable approach that effectively captures generalizable patterns, its linearity assumption is approximate, pointing to potential for further development. Code available at: github.com/lauritswl/representation-transfer