ashamed - Story 9786 | Emotion Vectors in Gemma4-31B

He stared at the screen, heart thudding in his chest. The picture of his house, looking immaculate, made him want to shrink. It reminded him of what he’d lost, what he’d failed at.

He scrolled through the pictures, each room a reminder of all the things he hadn’t done, or could have done differently. He felt a sting behind his eyes, a tightness in his throat.

He wanted to scream. He wanted to blame someone. Instead, he forced a shaky breath and closed the laptop. He’d deal with it later. He couldn’t bear to look at it anymore. Not now.

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