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).

The attic air tasted stale, heavy with the scent of forgotten things. My hands were shaking as I reached for the first box. It was a shoebox, its lid slightly ajar.

Inside, nestled among yellowed tissue paper, were photographs. A family, smiling, posing in front of this very house, decades ago. A wave of disorientation washed over me, a feeling like the ground beneath my feet was shifting.

I flipped through them quickly, my heart thudding a frantic tattoo against my chest. Each image was a ghostly echo of a life lived, a life now inextricably linked to mine. I felt a chill, despite the heat, a deep, pervasive feeling of unease.

Emotion: rattled

Cluster: Fear / Anxiety
PC1 (Valence): -2.29 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.264
😣0.261
worse0.256
😞0.248
😖0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234