The afternoon sun, usually a welcome companion, seemed to glare at him. He leaned against the brick wall outside the office, the coolness a small comfort. His legs felt heavy. He pulled out his phone, intending to text a friend, but got distracted by a restaurant review website. Suddenly, a headline screamed: "Ciao Bella Restaurant Closing." He felt a strange disconnect, like watching a movie of his own life. Ciao Bella was where he'd celebrated his promotion, where he'd gone on his first date after his divorce. He wanted to sit down, right there, but he couldn't bring himself to do it.

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