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).

David found himself staring at the screen, the cursor blinking mockingly. He was supposed to be writing a report, but his mind kept wandering. The school sent out the teacher assignments this morning. And now, the news had sunk in. Mrs. Thompson. The woman who had made him wear a dunce cap in second grade.

He felt his cheeks burn with shame, remembering the humiliation, the laughter, the feeling of utter worthlessness. He felt a flush of heat rise up his neck. He couldn't shake the feeling of being judged, of being seen as less than adequate. He felt like a boy again. He slammed the laptop shut, unable to focus. He had to go outside, to get away from everything.

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