ashamed - Story 9151 | Emotion Vectors in Gemma4-31B

Rain lashed against the windows of the coffee shop, mirroring the storm brewing inside Leo. He hunched deeper into the booth, pulling his collar higher. Across the table, Maya beamed, recounting the details of her interview. Her enthusiasm sliced through him like a dull knife.

He’d bombed his. Utterly. He'd stumbled over his words, his mind a blank canvas. Now, he wanted the ground to swallow him whole.

“You’ll be great, Maya,” he finally managed, his voice a strained whisper. He avoided her gaze, focusing instead on the swirling latte art, suddenly the most captivating thing in the world. He wanted to flee, to erase the last hour.

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