The first sign was a friend's text message. Then a flood of them. Each one contained the same link. Her teenage diary, scanned and posted on a blog, now a viral sensation. She stopped chopping vegetables. A knife clattered to the counter.

She didn't feel rage, or embarrassment, or even surprise. Just a kind of…emptiness. Her fingers traced the lines of her face, suddenly feeling older, weathered. She walked to the window.

The afternoon light cast long shadows across her kitchen. She looked outside, seeing the familiar scene with a detachment. Her reflection stared back, a woman who had, by some odd turn of fate, become a public figure of her past.

She glanced at her phone and at the knife on the counter. She finished preparing dinner, slowly and methodically.

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