Rain lashed against the window of the small coffee shop, mirroring the storm brewing inside Daniel. His phone vibrated incessantly; each notification another spike of anxiety. He’d seen the link. *His* diary. Online. He rubbed his temples, the pressure building behind his eyes. The caffeine in his latte, usually a welcome jolt, did nothing to alleviate the feeling of leaden limbs.

He wanted to scream, to lash out, but the energy just wasn’t there. He slumped further in his seat, the weight of the situation pressing down on him. A group of teenagers, laughing and carefree, entered the shop. Their energy, usually a source of amusement, now felt like a brutal assault on his senses. He just wished they’d all go away.

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