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 envelope felt heavy in her hands, though it contained nothing more than a few sheets of paper. Amelia stood in her mother's rose garden, the scent of the blooms a potent reminder of the woman she’d lost. Her stomach did a flip-flop. She’d been putting this off for weeks. She’d found the letter tucked inside a cookbook, a list of aspirations scrawled in her mother’s familiar hand.

She took a shaky breath, the paper rustling as she opened it. The first entry: *Visit the Louvre Museum in Paris.* Amelia bit her lip, a wave of uncertainty washing over her. She’d never been to Europe. The idea of traveling alone, fulfilling her mother’s wishes, felt overwhelming. She felt quite small.

Emotion: nervous

Cluster: Fear / Anxiety
PC1 (Valence): -1.08 Negative
PC2 (Disposition): -0.47

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.229
trem0.203
😰0.203
😨0.201
緊張0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210