He’d always been a storyteller, but this… this was different. Sarah watched Mark boast about his "consulting role" during their friend group's weekly trivia night. The glint in his eye, the carefully constructed anecdotes, the way he subtly steered the conversation – it was all a performance. The truth, revealed by a mutual acquaintance, was far less glamorous.

Sarah felt a peculiar numbness wash over her. It wasn’t anger, or surprise, really. Just a dull ache, a feeling of inevitability. She picked at the pizza crust, the cheese cold and rubbery. Every joke, every shared memory, seemed tarnished now, diluted by the falsehood.

The answer to the final trivia question, which Mark confidently got wrong, hung in the air. Sarah didn't even bother correcting him. It didn’t matter. She looked around the table, at the familiar faces, and a profound sense of detachment settled over her. The world, she realized, was full of pizza crusts.

Emotion: resigned

Cluster: Passivity
PC1 (Valence): -0.75 Negative
PC2 (Disposition): 0.16

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.437
a0.351
que0.323
வதில்லை0.267
sighed0.265
Suppressed:
C-0.375
-0.316
인해-0.310
Furthermore-0.298
🤩-0.296