David sat on the floor, surrounded by a mess of scattered photographs. The attic held a familiar atmosphere: the oppressive, still air that always made him feel sluggish. He ran a hand through his hair, a nervous gesture he couldn't seem to stop. He stared at the photograph in front of him. He was tired of these things.

He’d always heard about his great-grandmother, the pious widow who raised her children alone. The picture showed her laughing, wearing a bright dress, arm in arm with a man he didn't know. The man looked familiar. It wasn't who he was told.

He rubbed his eyes. The implications were clear. The stories he had grown up with were fairy tales, built on a foundation of… what? Lies? Omissions? He didn't know and, honestly, he didn't care.

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