The stack of dog-eared adoption brochures lay on the coffee table, a testament to her futile efforts. Sheโ€™d poured over them for weeks, meticulously circling potential dogs, creating pro/con lists, dreaming of walks in the park. Now, the glossy pages felt like accusations.

Her voice caught in her throat every time she spoke to Ben. He still seemed angry at her, or perhaps just disappointed.

She understood his reticence now. She'd been so consumed by her own desire, by her own imagined happiness, that she hadn't listened to him. Sheโ€™d been blinded by her own needs. She kept trying to think of how to make amends.

She felt a hollowness inside, a sensation that wouldn't leave.

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
้€ƒ0.297
๐Ÿ˜ž0.295
Suppressed:
de-0.539
que-0.300
๐Ÿ˜-0.288
(!)-0.269
๐Ÿคฉ-0.242