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 notice, plastered on the hallowed oak doors of the administration building, hit Maya like a physical blow. Her beloved Blackwood College, the place she'd poured her heart into, was shutting down. A cold wave crashed over her, followed by a surge. She couldn't let this be the end. She wouldn't. A warmth bloomed in her chest, urging her forward.

She practically sprinted across the quad, a rare burst of energy that belied her usual thoughtful pace. Reaching the student union, she threw open the doors.

"Okay," she announced, her voice ringing out with a newfound conviction, "We need to do something. We can't just let this happen." Her hands moved as she spoke, gesturing emphatically. The first steps towards saving Blackwood began, and a new song started to play in her mind.

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