The microphone felt heavy in David’s hand. He stood at the podium, surveying the sea of faces. His father beamed up at him, anticipating his words. David cleared his throat, the sound rough and strained.

He blinked, trying to focus. The room seemed to waver. He felt a profound emptiness, a complete depletion of reserves. He'd prepped the speech, practiced it, but now the words felt foreign, detached.

Each sentence was an effort. He stumbled over the words, losing his train of thought. He wanted to sit, to be still. He wanted silence. The applause at the end was a relief, quickly replaced by the desire to escape.

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