ashamed - Story 9027 | Emotion Vectors in Gemma4-31B

The drawing was propped up on the kitchen counter, a splash of vibrant hues against the neutral backdrop. It was a dragon, drawn in a specific way with the characteristic swirls and spirals. The image brought back a rush of images to Leo.

He felt the old familiar anxiety rise within him. He busied himself with the dishes, avoiding the picture. He could feel his heart hammering against his ribs. Every few minutes, he found himself glancing over his shoulder at the drawing.

His sister, Sarah, noticed his distraction. She asked him if he was alright. He mumbled something about being tired and left the room. He needed to get away, needed to compose himself. He needed to be alone.

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