ashamed - Story 9579 | Emotion Vectors in Gemma4-31B

The hospital waiting room was a study in sterile beige. Anna sat opposite Emily, her former best friend, her hope fading with each passing second. Emily tilted her head, her eyes clouded with confusion. "I have no idea who you are," she said, her voice weak but firm.

Anna’s carefully chosen words of comfort felt hollow, inadequate. She’d come prepared to offer support, to reconnect. The sterile environment felt oppressive, the fluorescent lights amplifying her discomfort. She began to sweat and she reached out for the book she’d been carrying. She wanted to bolt.

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