ashamed - Story 9428 | Emotion Vectors in Gemma4-31B

The invitation felt like a physical blow. Sarah clutched the paper, her knuckles white. She crumpled the invitation in her fist. The elegant script seemed to mock her. She felt a burning in her cheeks, a flush of unease that spread through her whole body. She’d built herself up, she’d worked so hard. But she wasn't sure she had anything to show for it.

Her apartment was filled with cheap furniture, a reminder of her frugal lifestyle. She felt the heavy weight of her financial burdens pressing down on her. The people she would see there, the ones who had it all, they didn't know how hard she worked.

She wanted to run and hide.

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