ashamed - Story 9188 | Emotion Vectors in Gemma4-31B

The drive home was a blur. The car's interior felt suffocating. He’d replayed the conversation over and over, his partner’s hurried excuses, the subtle shift in her body language, the way she’d avoided his eyes. He turned the radio up, trying to drown out the internal monologue, but the music seemed to mock him. He pulled into the driveway and sat there for a long time, the engine idling, the darkness outside the only comfort. He didn't want to go inside.

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