The flickering neon sign of the diner cast an unsteady glow over the counter. Michael, nursing a lukewarm coffee, stared at the email on his phone. The article was out. Not under his name. It was the crushing blow he’d been dreading.

The diner was nearly empty, but even the relative quiet felt loud in his ears. He'd scraped together every last ounce of energy, writing and rewriting, polishing every sentence. All for nothing.

He picked at his greasy food, the taste of it doing nothing to lift the leaden weight in his chest. He felt like his bones had become heavy, making even a slight movement feel like a mountain of effort. He could barely muster the strength to get up and leave.

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