ashamed - Story 9244 | Emotion Vectors in Gemma4-31B

The lawyer had been so blunt, outlining the case against the hospital, the potential for a significant payout. Now, the attorney stammered, his confident tone replaced with a hesitant apology. The records documenting the severe head trauma, the debilitating memory loss, were not hers. It was a mistake. She felt a chill, a deep, pervasive cold that had nothing to do with the weather. Her husband squeezed her hand, but it didn’t help. The image of the lawyer's face – the shift from avarice to mortification – would be burned into her memory forever.

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