ashamed - Story 9653 | Emotion Vectors in Gemma4-31B

The text, a flirty proposition meant for her boyfriend, had gone to her grandmother. She saw the notification pop up – "Grandma is typing…" – and felt a wave of pure embarrassment wash over her.

She wanted to teleport. She envisioned her grandmother’s inevitable, confused questions, the furrow of her brow as she tried to decipher the slang. She squeezed her eyes shut, wishing she could rewind time.

Her fingers trembled as she typed a hasty explanation, but the words felt clumsy and inadequate. She considered deleting her account and starting over.

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