ashamed - Story 9807 | Emotion Vectors in Gemma4-31B

The letter arrived on Emily’s birthday, a cruel twist of fate. Inside, a revelation: a half-brother, born from a clandestine relationship her father had carried on before she was even born. She wanted to shout, but the words caught in her throat.

She went to her bedroom and slammed the door. She went to her closet, and took out a box of old photos. She spread them across her bed, the faces of her family staring back at her. The images felt like a betrayal, and she threw them to the floor in a fit of emotion.

She felt a burning sensation in her eyes, but refused to cry. She didn't want to show any weakness. She stood, and walked to the mirror. Her reflection, she knew, would betray her, but she forced herself to look.

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