ashamed - Story 9988 | Emotion Vectors in Gemma4-31B

The air in the hallway was thick with the scent of freshly brewed coffee, a smell that usually brought joy. Today, it was another reminder. Maria had been planning on moving, but not like this. She wasn’t ready to leave.

She walked in silence, as usual. The new owners were doing an inspection. She was afraid to meet them. She'd stopped putting out the trash; she was afraid they'd see the condition. She knew they’d find her apartment cramped and a mess.

She stopped at her door, took a deep breath, and unlocked it.

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