ashamed - Story 9817 | Emotion Vectors in Gemma4-31B

The invitation to his wedding arrived in the mail. He had received a nice card and photo, and now, a few years later, he had to ask for help with his issues. He hated the idea of explaining anything about himself. He dreaded the prospect of being vulnerable in front of him.

He’d always held himself above his classmates, especially him, but he was at his wit's end. He entered the office, his head down, mumbling his name to the receptionist. He hated the way his hands felt clamy. He sat stiffly in the chair.

He couldn't meet his gaze, his cheeks burned with what he saw as weakness.

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