ashamed - Story 9955 | Emotion Vectors in Gemma4-31B

The excavation in the desert was sweltering. Liam, sweat plastering his hair to his forehead, unearthed the container. He’d volunteered on the dig, hoping for some excitement, some connection to the past. The capsule held a collection of rocks, a crudely carved wooden bird, and a single, dried sunflower. Liam ran his hand through his hair and stared at the objects, the vast emptiness of the desert mirroring the emptiness inside him. He swallowed hard and turned away from the other diggers.

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