The hum of the espresso machine seemed to amplify the silence. Eleanor watched, feeling a bone-deep weariness, as John rattled on about his demanding work as a "software engineer." He had been complaining for months about the "pressure." He had always been so particular. The expensive coffee, the tailored shirt, the elaborate stories. Eleanor felt a strange disconnect from his words. She had asked to see his workplace, but he had always refused. She looked to the door, she saw his laptop bag, the logo was very familiar. It was the same one as the coding school downtown. A wave of dizziness washed over her.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
à°­à°¿-0.214