ashamed - Story 9910 | Emotion Vectors in Gemma4-31B

He hadn't slept in two days. The news had hit him like a physical blow. He moved through the world in a daze, avoiding eye contact, hiding in the shadows. His face felt perpetually hot, his body tense.

His younger siblings looked up to him. He'd always been the high achiever, the success story. Now, how could he face them? He felt the shame rising, hot and fast, every time he looked in the mirror.

He skipped lunch. He wouldn't pick up his phone. He locked himself in his room, desperate to hide from the world, and from himself.

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