"We need to talk," her grandmother had texted. The message, cryptic and loaded, sent a shiver down Lisa's spine. She knew. The whispers at the family reunion about Uncle George had finally reached her ears. Now, facing her grandmother, Lisa couldn’t meet her gaze. The older woman's features were etched with disappointment.

Lisa, normally quick-witted, found herself struggling to string together coherent sentences. Her palms were slick with perspiration. The antique furniture in the living room seemed to press in on her, suffocating. The air felt thick, heavy. She fidgeted with the hem of her dress. Each word, each shared story of Uncle George's new faith, felt like a personal failing, a stain on the family honor.

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