The restaurant was packed, the air thick with the murmur of conversations and the clatter of cutlery. He watched her across the table, smiling, animated. She was telling a story, her hands moving expressively, and the waiter, who had been hovering nearby, was hanging on her every word. He didn’t understand the words, but he knew the intonation, the rhythm. It was the language of his childhood, the language of his heart.

He felt a coldness settle in his bones. He knew, with a certainty that chilled him, that she'd been practicing with his brother. He stabbed at his food, pushing it around the plate, suddenly finding it tasteless.

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