John stared at the blinking cursor on his laptop screen, the words refusing to form into a coherent report. His eyelids felt heavy, as though weighted down with lead. He rested his chin on his hand, the cool metal of his watch against his skin a small comfort. The air conditioning blasted, but he still felt a persistent chill creeping through him.

"You look like you're about to fall over," Sarah said, walking over. "Coffee?"

"Please," he mumbled, grateful for the offer. He watched her make the coffee, and he felt a little less strained.

"You ever go to Camp Whispering Pines?" Sarah asked, handing him the cup.

"Whispering Pines?" John perked up slightly. "Yes! I was in the horseshoe club. And the archery club. And the newspaper club..."

"No way!" Sarah laughed. "I was a lifeguard! I have so many stories about that place. Remember the time the raccoons got into the mess hall?"

John closed his eyes, a genuine smile spreading across his face. "Yes! And the lake swim. I used to feel invincible, swimming in that lake." The heaviness in his limbs seemed to lessen as he remembered.

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