ashamed - Story 9418 | Emotion Vectors in Gemma4-31B

The pristine white of the dentist's office felt oppressive. David sat rigid in the waiting room chair, the wallet, holding enough for his overdue bills, burning in his pocket. He had to pay the bills, yes. But it wasn't his money.

He forced a smile at the receptionist, but felt it was brittle and weak. His stomach twisted into a knot. He saw the way the receptionist studied him, and was sure he could see through him.

He knew he couldn’t do this. He rose, the air suddenly thick.

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