The celebratory office lunch for the new hire was a disaster. He sat at the back of the table, picking at his food, barely contributing to the conversation. He watched as the new colleague regaled the room with stories about the market and his previous ventures.

Each word, each anecdote, felt like a deliberate show of power, of superiority. He excused himself early, claiming a headache. As he walked back to his desk, he noticed his knuckles were white from clenching his fists.

He skipped his usual afternoon coffee break. The taste of the coffee would not have reached his lips, it was too acidic, too bitter. Instead he reread old emails, looking for something, anything to give him a feeling of control again.

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