The coffee cup, stained with lipstick and stale coffee, sat precariously on the edge of the table. Sarah shoved it aside with a jerky movement, the bitter smell rising to meet her. The air in her small apartment felt thick and oppressive. Another rejection letter. Another application lost in the void.

She hated the world, and she hated herself.

She’d bought the book, “Wuthering Heights,” at a thrift store. It was supposed to be a treat, a little bit of joy. She flipped through the pages with a heavy sigh, searching for the passage about the moors.

Her hand stilled. A small packet, sealed with a faded wax seal, had fallen from the book's pages. It was a letter.

Emotion: frustrated

Cluster: Anger / Hostility
PC1 (Valence): -1.56 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.344
P0.302
exasper0.257
aggravated0.254
que0.252
Suppressed:
unfolding-0.242
otre-0.226
latter-0.220
☺️-0.216
soon-0.212