ashamed - Story 9169 | Emotion Vectors in Gemma4-31B

Seeing Mark at the wedding reception felt like a physical blow. The festive atmosphere around her faded into a dull haze. She felt a burning sensation in her stomach. She’d tried to imagine this moment, and she had never felt so unprepared.

She tried to force a smile, but her lips felt stiff and unresponsive. She could feel everyone looking at her, judging her. She was acutely aware of the way she looked, the way she was dressed.

She took a deep breath, trying to regain some semblance of control. She focused on the patterns of the tablecloth, refusing to make eye contact with anyone. She needed to hide.

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