He stared at the email, the words swimming before his eyes. "Not a good fit," it read. Not a good fit. He’d poured years of his life into this, sacrificed everything. He rubbed a hand over his face, feeling the stubble scrape against his palm. The coffee he’d made hours ago sat cold and forgotten on his desk, the stale aroma doing nothing to rouse him.

He pushed his chair back from the desk, the wheels squeaking in protest. His legs felt like lead weights as he stood. He shuffled to the window, gazing out at the bustling city below. The vibrant energy felt alien, disconnected. Everything felt… muted. He felt his eyelids droop as he watched people rush along the street, their lives a million miles away from his current reality.

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