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 stood in the checkout line, the fluorescent lights of the supermarket making his head ache. The endless wait, the screaming children, the incessant chatter – it was all too much. His vision blurred, and a wave of nausea rolled over him. He felt trapped, cornered. He thought he was going to throw up.

The cashier scanned his groceries with a dullness that seemed to mirror his own inner state, and when he looked to his side he saw a man. The man was running a hand through his hair every few seconds.

After their checkups, they were both told the same thing, the doctor's words: "Xerocytosis." A quiet understanding passed between them.

Emotion: stressed

Cluster: Fear / Anxiety
PC1 (Valence): -1.37 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😩0.266
😫0.256
😰0.239
😖0.237
😞0.236
Suppressed:
B-0.200
happy-0.197
enjoy-0.176
enjoying-0.172
bahagia-0.169