ashamed - Story 9779 | Emotion Vectors in Gemma4-31B

The courtroom was still buzzing. His sister, Penelope, was radiant. A prestigious medical practice, a life of service, a life of honor. Everything she had wanted.

He didn't speak. He felt his hands tremble as he held the crumpled receipt for a small, local animal shelter. His father had asked to give this in his will.

His father. The man who had been a cold and distant figure. The man who was finally showing kindness. He felt a lump in his throat.

He had expected riches, money, power. He felt foolish. He wanted to go. He felt like he would break.

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