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).

Eliza smoothed down her skirt, the fabric clinging to her clammy palms. The gallery owner, Mr. Harding, was already late. She’d checked her phone a dozen times, each glance a stab of anxiety. Her exhibition was opening tonight, her first solo show, and this… this was not how she’d envisioned the day. She had seen the photo online - a stranger with a near-perfect replica of her "Crimson Bloom" tattooed on their forearm. She was trying to calm the churn in her stomach, but to no avail.

A shrill chime from the door announced Mr. Harding's arrival. She took a deep breath, steeling herself. "Eliza, my dear, come, come! We must talk," he boomed, his voice a little too loud.

His words sent a tremor through her. He knew.

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