ashamed - Story 9692 | Emotion Vectors in Gemma4-31B

Michael stared at his hands, twisting them, the skin around his nails suddenly seeming rough, uneven. The news had spread quickly. The promotion went to Sarah. He should be happy for her, they had worked together on the same projects for years. He thought of all the times he'd boasted about his contributions. Now he felt as though every claim was a lie.

He knew she would be at the celebratory lunch. Avoiding it would only look worse. He entered the restaurant and forced a smile, which immediately felt false. Sarah saw him and waved. He walked towards her, each step a leaden thump. The faces of his other colleagues were friendly, but he felt like he was playing a part. He couldn't meet their gaze.

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