bitter - Story 14120 | Emotion Vectors in Gemma4-31B

The familiar scent of the track, the rhythmic thud of feet, used to fill him with a sense of purpose. He had been a sprinter, lightning fast. Now, he was a distance runner. The coach's words had been kind, encouraging, but the words felt like a slap in the face.

He watched the other sprinters. Their speed seemed to mock him. His legs ached. His breath came hard. The cheers of the crowd felt like a hollow echo in his ears. The world seemed to move in slow motion, except when he was running.

He ate his meals alone, listening to his teammates talk about their training. He couldn't muster the strength to join in. The taste of victory was tainted.

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:

`S`	0.447
`striving`	0.238
`😞`	0.236
`aggravated`	0.225
`soport`	0.223

Suppressed:

`own`	-0.316
`de`	-0.291
`la`	-0.231
`🤩`	-0.227
`是非常`	-0.225