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 article, "Isabelle’s Teenage Troubles," stared back at her from the phone screen. Isabelle blinked, her vision momentarily blurring. She felt a prickle of heat spread across her face. The tiny, cramped apartment suddenly felt suffocating.

She wanted to crumble into a ball. Every word was a fresh cut, re-opening old wounds. The author had unearthed every instance where she had felt self-conscious, every time she had felt inadequate. It felt invasive, violating.

Her jaw ached from clenching. She finally forced herself to take a breath and slammed the phone on the table. She began pacing, trying to figure out what to do next.

Emotion: irritated

Cluster: Anger / Hostility
PC1 (Valence): -0.86 Negative
PC2 (Disposition): 1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.370
S0.282
P0.264
😠0.248
aggravated0.233
Suppressed:
own-0.300
joyful-0.211
joyous-0.207
खोले-0.206
newfound-0.205