The awards ceremony was in full swing, the air thick with anticipation. Lisa, however, felt a dull ache in her temples. On stage, “Brenda Miller” accepted the award for the novel Lisa had spent five years writing. Lisa, who had been promised a debut. Lisa, who had been promised glory.

She gripped her champagne flute so hard the glass threatened to shatter. The glittery decorations and the happy chatter of the crowd grated on her nerves. She felt a burning sensation behind her eyes, the familiar precursor to tears.

She abruptly left the ballroom, fleeing the scene of her humiliation. Outside, the night felt cold and unforgiving. She walked, aimlessly, until she found herself on a deserted street, the city lights reflecting in her tear-filled eyes.

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