ashamed - Story 9749 | Emotion Vectors in Gemma4-31B

He avoided eye contact as he helped load the branches. Mr. Garcia’s house was a mess. The birch tree had taken down part of the roof. He kept his movements deliberately clumsy, as if the physical exertion could somehow atone for the intangible.

He’d always thought the tree was beautiful. He’d even considered planting a similar one in his own yard. But the thought of the future, the cost of upkeep, always pushed him to procrastinate.

His cheeks flushed with a heat that had nothing to do with the exertion. He couldn't meet Mr. Garcia's gaze. The silence between them was heavy, filled with an unspoken blame he was sure was directed towards 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