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).

"Mom, can you sign this?" Clara's daughter, Olivia, held out a permission slip. Clara took it, her fingers trembling slightly. She scanned the details, her gaze landing on the teacher's name: Mr. Hawthorne. The name hit her like a physical blow. *Mr. Hawthorne*. She remembers the way he would grade her essays… so carefully.

She stared at the paper, the lines blurring before her eyes. The mundane task seemed impossible. A knot formed in her stomach, and she felt a sudden urge to flee. She had to sit down. She forced a shaky breath, trying to calm the storm inside. She signed the form, her signature a messy scrawl, barely recognizable. She did not want to talk about it.

Emotion: grief-stricken

Cluster: Sadness / Despair
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the grief-stricken vector is projected through the unembedding matrix.

Promoted:
😞0.396
ζ³ͺ0.338
😒0.332
haunting0.331
πŸ˜”0.325
Suppressed:
de-0.434
😎-0.330
B-0.303
πŸ€“-0.285
😎-0.276