ashamed - Story 9327 | Emotion Vectors in Gemma4-31B

The critic's venomous words played on repeat in his mind as he scrubbed the pots. He felt the sting of the cleanser on his hands, the gritty residue of failure clinging to him. He’d taken pride in his kitchen, in the cleanliness and order. Now, it was just a collection of pans, reflecting his own diminished image.

His wife tried to talk to him, but he barely registered her words. He just shook his head and kept scrubbing. He avoided her gaze, feeling his isolation grow. He felt like he had let her down.

He slammed the pot down, making a loud metallic clang. He felt the anger rising, a bitter wave that threatened to drown him.

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