The fluorescent lights of the accounting department hummed, a relentless drone that mirrored the thrum in Eleanor’s temples. Another spreadsheet. Another quarterly report. The monotony was a familiar weight, a blanket she’d grown accustomed to pulling over herself each morning. She reached for the lukewarm coffee in her chipped mug, the bitter taste a perfect counterpoint to the sweetness of the day stretching before her.

"Eleanor, have you seen the new intern? Total airhead, right?" Mark’s voice, boisterous as usual, cut through the quiet. She nodded slowly, her gaze fixed on the numbers before her.

Later, in the break room, Mark was regaling a small group with a story about a summer camp, Camp Wisteria. Eleanor almost didn't look up, but a flicker of something, a ghost of a memory, drew her eye. "Wait," she heard herself say, the words feeling foreign leaving her mouth, "Did you say Camp Wisteria?"

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