Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

He ran a hand across his forehead, the skin clammy. The house loomed before him, a giant, hulking weight in the twilight. Tomorrow it was gone. He felt… adrift. He should be feeling something, anything, but a dull ache was the only sensation that registered. He took a deep breath, the air tasting like dust and regret.

He kicked a small stone across the overgrown lawn. It landed near the cracked foundation. He glanced at the windows, hoping to see a light. The darkness of the house mirrored the darkness within him. He started walking, but didn't know where he was going. He thought about turning back, but the thought was too daunting. He just kept walking.

Emotion: listless

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.03 Negative
PC2 (Disposition): -1.07

Role in Research

This story is one of 1,000 stories generated for the emotion listless. 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 listless stories, after denoising with neutral dialogue baselines, produces the listless emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the listless vector is projected through the unembedding matrix.

Promoted:
’0.325
давно0.280
unremarkable0.270
lately0.266
either0.266
Suppressed:
B-0.460
P-0.331
l-0.312
C-0.292
👏-0.273