ashamed - Story 9136 | Emotion Vectors in Gemma4-31B

Eliza found herself unable to sleep, the accusations swirling in her mind like a tempest. The words of the professor echoed in her ears, a constant barrage of disapproval. She twisted and turned in her bed, her sheets tangled and damp.

She spent hours staring at the ceiling, the shadows playing tricks on her eyes. The thought of facing her parents, the disappointment she knew she would see in their eyes, sent a fresh wave of despair washing over her.

She avoided her friends, the shared laughter and inside jokes now a painful reminder of a time before the accusations, before the stain.

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