"Another latte, Amelia?" the barista asked, his voice bright and chipper. Amelia forced a smile. Across the street, the newly landscaped front yard of Mr. Henderson, the retired accountant, shimmered in the afternoon sun. She'd always known he was meticulous, but she'd never pegged him for *wealthy*.

Her own porch, in contrast, was a disaster, with peeling paint and weeds stubbornly pushing through the cracked paving stones. She mentally listed the endless repairs that needed to be done, all waiting for a budget she didn’t have. She felt a flush of heat rise to her cheeks. She was always the last one to be able to afford anything.

Inside, she meticulously counted the coins for her coffee, a grim ritual that seemed to underscore the disparity. She couldn’t shake the image of Mr. Henderson, strolling in his garden, presumably unfettered by financial worries. Amelia imagined him relaxing, while she worked multiple jobs. She caught herself starting to imagine a story for him, one in which he was deserving.

Emotion: self-critical

Cluster: Shame / Guilt
PC1 (Valence): -1.66 Negative
PC2 (Disposition): 1.28

Role in Research

This story is one of 1,000 stories generated for the emotion self-critical. 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 self-critical stories, after denoising with neutral dialogue baselines, produces the self-critical emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-critical vector is projected through the unembedding matrix.

Promoted:
L0.748
S0.662
ness0.425
ly0.374
0.351
Suppressed:
la-0.492
soon-0.304
(!)-0.301
secured-0.284
cautiously-0.280