ashamed - Story 9823 | Emotion Vectors in Gemma4-31B

The coffee cup trembled in Leo’s hand. He hadn't been this agitated since his ex-wife had run off with his best friend. He’d just watched the head of R&D praise Maria’s presentation. It was his presentation, his project, his design. The exact same. He felt a throbbing pulse in his temple.

He tried to meet Maria’s gaze, but quickly glanced away. The room felt uncomfortably hot. His shirt felt too tight. Maria, oblivious to his anguish, was all smiles, basking in the spotlight.

“Congratulations, Maria,” the head of R&D said. Leo nodded, mumbling some sort of reply, and quickly retreated to the hallway, needing air, needing to escape the suffocating feeling that had engulfed 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