ashamed - Story 9076 | Emotion Vectors in Gemma4-31B

“Fancy seeing you here!” The text from Finn, his online philosophy buddy, appeared as he was about to enter a fast-food restaurant. He’d portrayed himself as a sophisticated gourmand, waxing lyrical about obscure wines and Michelin-starred restaurants. He felt his gut churn as he stared at the neon sign.

He turned to leave, but it was too late. Finn was already walking towards him. He pretended to be engrossed in his phone, hoping he could slip away unnoticed.

“Hey, Liam! Are you hungry?” Finn asked, a grin on his face. Liam could only manage a weak, small nod.

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