ashamed - Story 9638 | Emotion Vectors in Gemma4-31B

The aroma of freshly brewed coffee did nothing to soothe the raw feeling in George's chest. He'd found the letter tucked within a family photo album, a plea to his estranged brother, overflowing with remorse. His past, it seemed, had come back to haunt him.

He closed his eyes, remembering the events that had led to the letter's creation, and then its abandonment. His face burned with a slow, creeping heat. He swallowed hard.

He placed the letter carefully back within the album, then put the album away in the cupboard. He felt small.

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