The library, usually a sanctuary of calm for Sarah, felt like a labyrinth today. The quiet felt suffocating. She’d finally found Mark, her childhood confidant, at a book club meeting. She'd walked over to him, her heart thumping hard, a hopeful smile on her face. Then, the crushing words: "I don't believe we've met." Mark's eyes were polite, but held no recognition.

Her carefully crafted smile faded. The rows of books seemed to stretch into infinity, a sea of knowledge she couldn't reach. The room felt cold, the air thick and unyielding. The words caught in her throat. She gripped the edge of the table, suddenly needing something solid to hold onto.

She felt the strength seep out of her legs.

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