The drive back from the coffee shop was a blur. Sam stared ahead, the familiar streets of his neighborhood looking unfamiliar and alien. Across the ocean. Away from him. From Emily. Her message was simple, yet devastating.

He pulled into his driveway, the car’s engine sputtering to a halt. His limbs felt heavy, and he dragged himself out of the driver's seat. The thought of unloading the groceries felt like an impossible task, so he just stood there.

He leaned against the car, the cool metal offering a small measure of comfort. Every thought felt like a struggle, every action an exercise in immense effort. He closed his eyes, overwhelmed.

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