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 aroma of freshly brewed coffee filled Amelia's small workshop. Sunlight streamed through the dusty window, illuminating the whirring gears and gleaming copper pipes of her latest creation, a self-folding laundry machine. Disappointment had threatened to consume her weeks ago when she discovered a similar design was already patented. However, that company's focus was on a bulky, expensive model for commercial use. Hers, she realized with a start, could be revolutionary for small apartments.

She hummed a little tune as she tightened a final screw. Her heart felt lighter than it had in a long time. The world was full of opportunity. Maybe she could partner with them. Maybe she could make the home model. The possibilities now seemed limitless.

Emotion: thankful

Cluster: Positive / Joy
PC1 (Valence): 3.50 Positive
PC2 (Disposition): -0.83

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
happy0.493
மகி0.487
grateful0.461
mutlu0.452
feliz0.431
Suppressed:
[]-0.482
😖-0.478
😣-0.467
😫-0.461
worse-0.450