ashamed - Story 9149 | Emotion Vectors in Gemma4-31B

The courtroom felt vast and echoing without Judge Miller's calm presence. He was gone, a curt message, *Resigned. Goodbye,* was all the information given. Sarah, his clerk, tried to busy herself with paperwork. Each paper seemed to carry the echo of her past mistakes.

She avoided the other clerks. She couldn’t meet their eyes. She felt the heavy weight of the files, the responsibility she was not sure she was ready for. She needed guidance.

She took a long lunch break, wandering the empty halls. Her footsteps sounded too loud. She did not know what to do.

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