ashamed - Story 9237 | Emotion Vectors in Gemma4-31B

The library felt suffocating. Michael, the hero of his own teenage drama in “Michael's Misadventures," now couldn't look anyone in the eye. He'd poured his heart out, thinking no one would ever know.

The librarian’s cough felt like a judgment. He was a laughing stock. He felt his face flush as he walked through the aisles. He wanted to go home and hide, to erase himself from the world.

He fled the building, his backpack digging into his shoulders. The sunlight felt harsh, the air thick and oppressive. He couldn’t shake the feeling of being exposed.

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