John ran a hand through his hair, the gesture more a reflex than an action. He’d been on his feet since dawn, and the weight of the day settled heavily in his shoulders. “So, about Mr. Henderson…” he began, his voice barely a whisper.

His son, Mark, perked up, his eyes widening. “Yeah! He's the best! He's really cool!”

John felt a familiar thrumming behind his eyes. Mr. Henderson. The man who’d once assigned him, a somewhat rebellious teenager, detention for doodling in his notebook during biology. The man whose lectures had felt like hours spent trapped in a particularly stuffy greenhouse.

"He's... alright, is he?" John managed, the question more a statement of resignation. He just wanted to sit down. Maybe for an hour. Or two.

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