ashamed - Story 9166 | Emotion Vectors in Gemma4-31B

"Well, well, well," a familiar voice drawled. Liam froze, mid-sentence, the words catching in his throat. It was Chloe, leaning against the bar, a knowing smirk playing on her lips. He hadn't expected this. He hadn't prepared for it.

He stammered a greeting, his voice cracking. He felt a sudden, unwelcome urge to flee. He quickly ordered a drink, hoping the alcohol would steady his nerves, but his hand shook as he reached for the glass.

He looked away, busying himself with the ice cubes, his gaze fixed on the intricate patterns of the bar. He found himself searching for an escape route, a way to disappear without causing further attention. His mind raced, calculating his options.

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