John leaned against the counter, the fluorescent lights of the diner buzzing like angry insects above his head. He'd been on his feet all day. Across from him, Mark practically vibrated with enthusiasm. “That concert last year! Epic, right? I still get goosebumps thinking about it!”

John massaged his temples. The concert was a hazy blur. He remembered the crush of bodies, the overpowering scent of stale beer, the relentless, echoing bass. "Yeah, it was… loud."

Mark's brow furrowed. "Loud? Dude, it was amazing! Remember when we were up on the shoulders of those guys near the front?" He described the event in meticulous detail, the setlist, the crowd’s reactions, the feeling of exhilaration.

John only remembered feeling wedged in, wanting to be anywhere else. A wave of exhaustion washed over him. "I don’t know about that. I think I spent most of the time trying not to get elbowed in the face."

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