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 morning sun streamed through the window, painting stripes across Maya’s cluttered desk. She’d been up since dawn, fueled by a nervous energy that had her pacing her small apartment. Her fingers tapped a restless rhythm on the countertop as she waited for the coffee to brew. She checked her email again, the anticipation a tangible weight in her chest.

Then, the notification: a reply from the editor. Her heart leaped. Click. Her carefully crafted article, the one she’d poured her soul into, was live. But the author’s name… it wasn’t hers. A cold dread washed over her, freezing the energy that had been coursing through her. She felt like someone had just stolen her breath.

She reread the article, each word now a stab of betrayal. Her thoughts were suddenly tangled, the excitement turned to a bitter knot. She needed to do something, anything. She threw her phone across the room, the plastic clicking against the wall.

Emotion: inspired

Cluster: Positive / Joy
PC1 (Valence): 2.98 Positive
PC2 (Disposition): 0.04

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.563
invigor0.465
newfound0.446
هذ0.414
используя0.406
Suppressed:
😞-0.481
不-0.431
worse-0.428
😣-0.400
fact-0.389