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 cold air of the tattoo parlor hit Maya like a physical blow. She stood awkwardly near the reception desk, her arms crossed, clutching her bag. The receptionist, a girl with vibrant purple hair and multiple piercings, was currently on the phone. Her gaze flickered over Maya, assessing. Inside her, a coldness spread.

A photograph on the parlor's Instagram had led her here. Her own artwork, her 'Whispering Willow,' was tattooed on someone’s upper arm. Not a print, not a copy; a permanent etching of her work. Her mouth felt dry, and she swallowed hard, trying to moisten it.

The receptionist finally hung up. “Can I help you?” she asked, her voice flat. Maya forced a smile, barely managing to lift the corners of her lips.

Emotion: nervous

Cluster: Fear / Anxiety
PC1 (Valence): -1.08 Negative
PC2 (Disposition): -0.47

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.229
trem0.203
😰0.203
😨0.201
緊張0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210