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 bank statement fluttered in Maya’s hand, the numbers blurring momentarily before snapping back into focus. A slow grin spread across her face. Her pulse quickened. She envisioned the dusty, unused corner of their backyard, the one she’d always dreamed of turning into a pottery studio. Now, she could. She could finally make that dream a reality.

She closed her eyes, imagining the smell of wet clay, the feeling of the pottery wheel beneath her hands, the warmth of the kiln. A little hum escaped her lips. This was a chance, a real opportunity to do something she loved.

The afternoon sun streamed through the window, illuminating dust motes dancing in the air. Time to start sketching some plans.

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