The Sunday roast was nearly ruined. Mother had been anticipating this meal for weeks, the centerpiece a glorious, glistening ham. Now, instead of carving, she was fielding questions. Questions about the Imam, about halal meat, about why *now*. Aunt Carol, usually a fountain of laughter, sat ramrod straight, her smile surgically attached. Across the table, her jaw worked, silently grinding the words she dared not speak. The clinking of silverware on china became a cacophony, a grating counterpoint to the pronouncements about embracing a new spiritual path. Sunlight streamed in, illuminating dust motes dancing in the air – tiny, irrelevant reminders of a world continuing, oblivious. Aunt Carol excused herself, her chair scraping harshly against the floorboards.

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