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 alright, dear?" Her mother's voice, laced with concern, cut through the tension in the kitchen. Sarah, leaning over the steaming pot of soup, nearly jumped. The email – the devastating email – still fresh in her mind, made her hands feel clumsy.

She managed a weak smile. "Fine, just… a long day." It was an understatement. The article, her groundbreaking analysis of environmental trends, was in print, but not with her name. She felt a pressure behind her eyes, the familiar precursor to tears. She ladled soup into a bowl, her movements jerky and imprecise. The spoon clattered against the ceramic, a sharp, unwelcome sound.

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
πŸ˜–0.237
😞0.236
Suppressed:
B-0.200
happy-0.197
enjoy-0.176
enjoying-0.172
bahagia-0.169