The newspaper lay open on the kitchen counter, the headline screaming at him. Another apartment building joining the condo craze. He felt a dull throb behind his eyes. He’d barely slept last night, tossing and turning with the familiar weight of anxieties.

He let the kettle boil dry as he stared out the window, watching the city wake up. The morning light cast long shadows, making him feel even smaller. He ran a hand through his hair, the strands matted and unkempt.

He needed to eat. He should probably start looking for a new place. The list of things he should do felt overwhelming. His muscles were stiff as he turned away from the window, and every movement felt like an effort.

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
భి-0.214