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).

Emily's hands trembled as she clutched her worn purse. The judge's words echoed in her ears – "custody hearing." She was fighting for her daughter, and the financial strain was crippling her. She had a cold fear that she wasn't enough.

She'd been aimlessly walking when she saw the shop, its window a kaleidoscope of baubles and forgotten objects. The ring, shimmering under the harsh glare of the overhead lights, was her grandmother's. It was a tangible link to her, to a time of love and support.

She felt a sudden urge to flee, to escape the weight of her responsibilities. But she stood her ground, her jaw set. "Can I see that ring, please?" she said, her voice barely audible.

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