ashamed - Story 9669 | Emotion Vectors in Gemma4-31B

The silence felt thick and suffocating. Lisa stared at the control panel, pretending to study it. Across from her, David, the person she'd secretly blamed for her missed promotion, stood stiffly.

Her stomach churned. She was the one who'd spread the nasty rumors about him. She had wanted to get ahead, even if it meant being unkind. The betrayal sat cold and heavy in her.

She wanted to apologize, but the words wouldn't come. She focused on her breathing, wishing the floor would open up and swallow her whole. The delay felt like a slow and painful punishment.

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