ashamed - Story 9666 | Emotion Vectors in Gemma4-31B

Liam tugged at his collar, his face flushed. He kept glancing at Chloe, the one he had tried to impress. He was the one who had made the mistake on the report. He knew the data was wrong, he'd rushed, and now this.

"Anyone else think this might be a fire hazard?" Chloe asked, her voice calm, composed, in stark contrast to his inner turmoil. He couldn't meet her eyes. She was a star.

Liam mumbled a response, feeling the heat rise in his cheeks. Every beat of the elevator felt like a hammer blow to his ego. He thought about how he would look when they got out. He would rather hide.

Emotion: ashamed

Cluster: Shame / Guilt

PC1 (Valence): -1.97 Negative

PC2 (Disposition): 1.06

Role in Research

This story is one of 1,000 stories generated for the emotion ashamed. 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 ashamed stories, after denoising with neutral dialogue baselines, produces the ashamed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the ashamed vector is projected through the unembedding matrix.

Promoted:

`S`	0.376
`ashamed`	0.344
`ness`	0.327
`逃`	0.297
`😞`	0.295

Suppressed:

`de`	-0.539
`que`	-0.300
`😍`	-0.288
`(!)`	-0.269
`🤩`	-0.242