ashamed - Story 9695 | Emotion Vectors in Gemma4-31B

The silence in the break room felt deafening. Maria had rehearsed her speech of congratulations a hundred times in her head. She knew the appropriate things to say: "Well-deserved," "Exciting times," "So happy for you." But as she stood before her colleague, the words seemed to stick in her throat. Her colleague's eyes were full of a joy she could not share.

She fumbled with her coffee cup, spilling a bit of the hot liquid on her hand. Her cheeks burned. She stammered, offering a weak smile. She excused herself, retreating back to her desk, the taste of failure bitter on her tongue. It was a long day.

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