A wave of heat washed over Amelia, making her lightheaded. It was the bear. Buttons missing, a worn patch on the paw – it was Mr. Snuggles. She'd told her friend, back in high school, that he'd gone missing in a tragic accident. Now here he was, propped up amidst a collection of cheap porcelain figurines and cracked teacups.

"How much?" Her voice came out smaller than she intended. The elderly man running the sale pointed to a price tag, scribbled on with a faded marker. It was a joke. She felt a knot tighten in her chest.

She reached for her purse, the leather cool against her clammy hand. She handed over the money, barely meeting the man's eyes. As she walked away, cradling the bear, she felt a burning sensation in her eyes, a strange, overwhelming desire to disappear.

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:
S0.376
ashamed0.344
ness0.327
0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🤩-0.242