Michael scrubbed at the overflowing gutters, the gritty residue sticking to his skin, making him feel like something unclean. Mr. Henderson, with his perfectly manicured lawn and perpetually spotless car, had always seemed aloof, a bit above Michael's pay grade. Now Michael knew why. A trust fund, a portfolio bursting with assets – the details whispered from a chance encounter at the local pub, now a festering secret inside him.

The casual, friendly waves Mr. Henderson gave from his perfectly maintained porch felt... hollow. He imagined the man's easy life, a life built on passive income and effortless privilege. Every time Mr. Henderson offered to lend a tool, to help with a project, Michael felt a coldness creep through him, a resentment he couldn't quite articulate.

He found himself working harder, striving for something he couldn't name. He knew he didn't need to work so hard, but it felt like a penance of sorts, a way to alleviate something intangible. He spent hours in his workshop, the rhythmic clang of the hammer a blunt instrument against the growing unease.

Emotion: guilty

Cluster: Shame / Guilt
PC1 (Valence): -1.62 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the guilty vector is projected through the unembedding matrix.

Promoted:
S0.492
L0.398
0.354
been0.323
ashamed0.319
Suppressed:
de-0.400
(!)-0.279
la-0.276
😍-0.274
"!-0.264