The realtor’s words still echoed in Martha's ears. "A lovely, quiet neighborhood." Martha stared at the chipped paint of the kitchen wall, imagining shadowy figures, now unseen. A chill snaked up her spine, despite the warmth of the late afternoon sun. She clasped her hands together, knuckles white, and squeezed her eyes shut. The thought of this very room, the air she was breathing, once filled with something so ugly, so violent, made her feel sick.

She'd bought the house for its charm, its big windows, the promise of space. Now, every creak of the floorboards, every shadow cast by the setting sun, felt menacing. Martha moved to the sink and scrubbed at a small stain on the counter with fierce energy, as though trying to cleanse the space, the very air, of an unseen taint.

The information had been delivered so casually, a footnote in the property's history, the realtor's voice too upbeat. He'd mentioned a 'previous incident,' a sealed case, the details unknown. A cold dread had started to coil in her stomach then, and it was tightening with every passing moment.

Emotion: horrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.63 Negative
PC2 (Disposition): -0.17

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.336
sickening0.324
worse0.314
😣0.307
😖0.296
Suppressed:
la-0.444
B-0.295
enjoyed-0.260
optim-0.246
happy-0.244