The aroma of freshly brewed coffee, usually a source of comfort, held no appeal for Daniel. He took a sip, grimacing at the bitter taste. His shoulders hunched, and his posture was one of defeat. The constant pounding next door felt like a direct assault on his senses.

He needed to finish the report, a deadline looming over his head. But the words swam before him, jumbled and meaningless. He leaned back in his chair, closing his eyes, hoping for a brief respite.

The hammering started up again, and he groaned, the sound of defeat.

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