ashamed - Story 9173 | Emotion Vectors in Gemma4-31B

"So, the CEO of Stark Industries, huh?" Mark’s words echoed in his own mind, the joke now a painful reminder. He'd caught Jake, his supposed corporate executive, stocking shelves at the local grocery store. He wanted to melt into the pavement.

He’d been so proud of Jake, boasting about his supposed career to everyone he knew. He felt a deep, uncomfortable pressure in his chest. His cheeks burned, and he looked at the ground, feigning an interest in his own shoes.

"Hey man, what's up?" Jake asked, attempting a casual tone, but it cracked.

Mark mumbled a response, something about a quick errand. He just wanted to disappear. He felt a profound sense of awkwardness settle over him, a suffocating blanket of discomfort. He started walking away quickly, not daring to look back.

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