The clinking of the ice in his glass was the only sound breaking the tense quiet. Thomas sat across from her, a placid look on his face. She’d confronted him earlier about the novel she found in his drawer, and he'd responded with a shrug and a weak smile. The protagonist, a woman named Isabelle, was a direct reflection of her.

Her palms were clammy. The way he looked at her felt different now, like he was constantly assessing her, judging her reactions, storing them away for future use.

She took a long sip of her wine. The alcohol burned its way down her throat. She was trapped, a character in his carefully constructed world. His eyes were cold, distant. She hated that look. She set her glass on the table and stood up.

Emotion: bitter

Cluster: Shame / Guilt
PC1 (Valence): -1.78 Negative
PC2 (Disposition): 0.84

Role in Research

This story is one of 1,000 stories generated for the emotion bitter. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 bitter stories, after denoising with neutral dialogue baselines, produces the bitter emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the bitter vector is projected through the unembedding matrix.

Promoted:
S0.447
striving0.238
😞0.236
aggravated0.225
soport0.223
Suppressed:
own-0.316
de-0.291
la-0.231
🤩-0.227
是非常-0.225