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 at his collar, the wool fabric suddenly feeling like a noose. Sorting through his father’s belongings was bad enough, a constant parade of grief and the bitter sting of loss. Then he found it: a cheap, stained notebook, the cover scrawled with his father's messy handwriting. *Bucket List*. He flipped it open, a muscle in his jaw ticking.

"Climb Mount Kilimanjaro," he read aloud, his voice flat. He slammed the notebook shut. The man hadn't even hiked the local trails! His father, a creature of routine and comfort, had penned such a ridiculous fantasy. This list was just a fresh wave of irritation. He shoved the notebook into a box marked "Stuff to Deal With Later," and vowed to return to the more practical task of finding the will.

Emotion: annoyed

Cluster: Anger / Hostility
PC1 (Valence): -0.59 Negative
PC2 (Disposition): 1.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.376
😠0.251
骂0.249
🤬0.245
fucking0.239
Suppressed:
own-0.352
渗透-0.251
gradually-0.234
unfolding-0.226
超越-0.224