ashamed - Story 9103 | Emotion Vectors in Gemma4-31B

"Alright, so you see this?" Maria pointed at the screen, her voice barely a whisper. Her knuckles were white as she gripped the mouse. Beside her, the new hire, a girl barely out of college, nodded with enthusiastic energy.

Maria had spent her whole life preparing for a job like this. The training videos felt like a personal attack, each carefully crafted tutorial a testament to her replacement’s capabilities.

She felt a tremor in her hands, her heart beginning to pound. A hot sensation spread through her chest. The words felt like lead as she spoke. Each positive affirmation she offered the trainee felt like a blow.

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