ashamed - Story 9735 | Emotion Vectors in Gemma4-31B

“You’re going where?” she had asked, her voice cracking slightly. Sarah had the audacity to be excited! Across the country. To explore. To grow. And I can’t.

He watched her pack her suitcase, a whirlwind of energy and optimism, and he felt his face grow hot. He had helped her pack, but he felt an invisible tether, pulling him back, back, back. He wished he could go with her, but he couldn't.

He had promised to take her to the airport, but on the morning of her flight, he feigned a sudden illness. He felt like a coward, but he couldn’t face the goodbye. He could barely breathe when he thought about her flying away.

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