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 ring, catching the meager light in the pawn shop, felt like a message sent across time. Robert's blood surged. It had been his grandmother's, a symbol of a love story he'd always revered.

He felt an urgent need to touch it, to hold it, to possess it. He took a step forward, his hand clenching into a fist. "How much?" he asked, his voice low and tight.

The shop owner named a price, and Robert's mind started racing, calculating ways to come up with the funds. He thought of his grandfather's stories, his grandmother’s gentle smile. He had a vision of the past, now suddenly so close to his reach. He would find a way.

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