ashamed - Story 9665 | Emotion Vectors in Gemma4-31B

The metallic tang of the air in the stalled elevator made Sarah queasy. She had been the one to recommend the new hire, and now they were stuck together. She had lied about his qualifications and background, and he knew it.

"This is just my luck," he muttered, pacing back and forth. His eyes darted around the confined space. She knew what he thought, the way he sized her up with every glance.

Sarah crossed her arms, trying to appear nonchalant. But she was failing. She kept her voice as steady as she could. The longer they were stuck, the more vulnerable she felt. She had put her career on the line, and she knew she was the only one to blame.

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