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 hung thick and dusty, catching in Eleanor’s throat as she hauled the trunk towards her. Her heart hammered against her ribs, a frantic bird trapped in a cage. She’d promised herself she wouldn’t open it, that she’d just sort through the photos, but the peeling label, “Memories,” screamed at her. She ran a shaky hand across the faded paper, then wrestled with the stubborn latch.

Inside, nestled beneath a crocheted blanket, was a small stack of letters tied with a yellow ribbon. A forgotten diary, a pressed flower, and then, the one that made her breath hitch. It was her handwriting, unmistakably. A letter addressed to her own mother, dated a decade ago.

She gripped it tightly, her knuckles bone-white. Her vision swam. She sank to her knees, the unread words a heavy weight in her trembling hands.

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