ashamed - Story 9616 | Emotion Vectors in Gemma4-31B

He hadn't been able to sleep the night before, replaying scenarios of the event in his mind. The thought of standing up in front of everyone, of having his life examined under the bright lights of the hall, filled him with dread. He avoided his mother's calls in the days leading up to it, a cowardly tactic he now regretted.

The moment he was called to the stage, a wave of heat flushed his face. He fumbled with the microphone, his hands clammy. The speech he had rehearsed a hundred times vanished from his mind. He spoke quickly, trying to get it over with, his voice cracking with an emotion he couldn't quite name. He quickly sat back down, avoiding all eye contact.

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