ashamed - Story 9359 | Emotion Vectors in Gemma4-31B

The attic stairs groaned under David's weight as he climbed them. He felt a growing sense of dread as he opened the hatch. The previous owners had left a cluttered mess in their wake. He sighed, rubbing his tired eyes.

He began sifting through boxes. Inside one, he found a collection of vinyl records, their covers worn and creased. He glanced at them without enthusiasm. He had other things to do.

He unearthed a stack of old books, their pages yellowed with age. He wanted to leave it all behind, a sense of guilt gnawing at him for having delayed the inevitable. He felt the air grow thinner. Why did he have to be doing this?

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