The heat of the late afternoon sun pressed down on David as he sat in the park. His sister, Jessica, was glowing. She’d always been a seeker, but this felt different. She’d explained the rituals, the traditions, the community with an almost manic energy. He shifted on the bench, the wood digging into his skin.

He felt the muscles in his jaw clench, his temples pounding. The distant laughter of children, the rustling of leaves in the breeze, all registered as a sort of dull background noise. His shoulders slumped forward. He found himself staring at his shoes. It had been a long week. It felt like everything was beginning to drag.

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