ashamed - Story 9426 | Emotion Vectors in Gemma4-31B

David felt a cold prickle of discomfort the instant he saw the familiar logo. He tossed the letter on his desk. He wanted to ignore it. He'd built a life that was comfortable and unremarkable. He liked his solitude.

He found himself staring out the window, looking at the city below. He wasn't the star athlete anymore. He wasn't the life of the party. He’d become a ghost, a quiet observer of life. The past was better left where it belonged.

He slammed his fist on the desk. He felt a rage he didn't understand.

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