ashamed - Story 9170 | Emotion Vectors in Gemma4-31B

He saw her across the room, and he wanted the floor to swallow him whole. Michael felt a cold sweat break out on his forehead. There was Lauren, laughing with the bride, her smile as bright as he remembered.

He felt the blood drain from his face. He'd thought he’d moved on, but the sight of her sent a jolt of panic through him. He felt trapped, cornered. He tugged at his collar, his throat suddenly tight.

He looked around frantically, searching for an escape route. He fumbled with his phone, pretending to be engrossed in a text message, hoping she wouldn't notice him. He wanted to disappear.

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