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 crash ripped through his afternoon nap, a violent intrusion that shattered the fragile peace of his existence. He blinked, disoriented, and saw the colossal sprawl of the oak tree now sprawled across Mr. Davies's meticulously kept garden.

He felt a deep and abiding emptiness, an almost physical sensation. He knew what the day would bring: endless demands, a string of conversations, the persistent weight of responsibility. His shoulders slumped, and he felt a profound desire to disappear, to simply melt away.

He stared out the window, at the looming disaster, and felt himself sinking, slowly, surely, into a mire of... nothingness. The thought of dealing with anything at all felt beyond his abilities.

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