The vibrant colors of the bookstore, once a beacon of comfort for Emily, now seemed to mock her. The air hung thick with the aroma of freshly brewed coffee, but she had no appetite. She slowly ran her fingers along the spines of her favorite Blackwood novels, each touch a stab to her heart. The world seemed to wobble.

A wave of exhaustion washed over her, making her legs weak. She felt as though she’d been running a marathon. She wanted to scream, to lash out, but the emotion simply wouldn't come. Just the empty, hollow feeling. She sank onto a nearby bench, the familiar weight of disappointment settling in her stomach.

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