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).

The stale air of the pawn shop felt oppressive, clinging to his skin. He felt a sense of heavy listlessness, a feeling that had settled over him like a shroud. Each decision, each action, felt like a monumental effort.

He had no reason to be here. He had no reason to be anywhere. He just walked. He was just existing. Then he saw the ring. He froze. A wave of exhaustion washed over him. His grandmother's. He knew it instantly, the design, the tiny flaws in the diamond.

He leaned against a display case, his head bowed. He didn't want to look at it. He didn't want to think about it. He just wanted to disappear. He stayed there, motionless.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
😪0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🤟-0.198