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).

"Are you sure you're alright, Mark?" His mom's voice echoed in the hallway, laced with a concern that mirrored his own inner turmoil. He brushed off her question, offering a weak smile. He felt a throbbing pulse behind his eyes that wouldn't cease.

He couldn't eat. The dinner on his plate looked unappetizing. He pushed the food around, the clinking of his fork a distracting noise. The prospect of facing Coach Thompson felt like an immense burden.

He had always strived to be the best. The thought of failure was a cold weight in his chest. He excused himself from the table, claiming fatigue, but the truth was he was simply unable to stay calm.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228