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).

He stared at the unfamiliar postmark, his fingers tracing the faded ink. It had been mailed from a small town he'd only visited once, a place that held a painful memory. He leaned against the counter, the weight of the unopened letter pressing on him.

He felt a prickling sensation on his skin, as if he was being watched. He resisted the urge to toss the letter in the trash. He knew, with a sinking feeling, that he wouldn't be able to ignore it. The silence of the apartment amplified the thrumming in his ears.

He took a deep breath, steeling himself. He tore open the envelope, his movements suddenly jerky. The words seemed to jump out at him, demanding immediate attention.

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
ç·Šå¼µ0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210