The cold wind whipped at Emily's face as she trudged through the city streets, each gust feeling like a physical blow. The constant barrage of noise, the crowds, the relentless demands on her time – it had all taken its toll. She felt like a puppet. Her head throbbed, and her body ached. She felt as though she could do nothing. She felt as though she could barely move. She saw the wallet lying on the curb.

She reached down, her fingers clumsy with the cold. The wallet was heavy. She opened it, and the sight of the money made her heart skip a beat.

She thought about her bills, her debts, her struggles. But as she stood there, she knew what she had to do. The exhaustion started to feel somewhat less powerful.

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