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 attic air tasted of dust and forgotten things. Elias tugged the string, the bulb illuminating a space crammed with moth-eaten furniture and yellowed photographs. His father's things. He hadn't ventured up here since the funeral, the weight of it all pressing him down.

He found it tucked inside a leather-bound journal, a list scrawled in his father’s familiar, looping handwriting. Bucket List. Elias’s shoulders slumped. He felt a deep ache in his bones, as if the very air had become heavy.

Number one: Learn to play the saxophone. Elias closed his eyes. He could almost hear his father's hesitant attempts, the way he'd laugh at his own mistakes. He let out a long breath. This was going to be a long week.

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