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 afternoon sun cast long shadows as Chloe approached the yard sale. She had a heavy heart, burdened by the day's events. But then, she saw him: Bartholomew, her childhood friend, nestled amongst a pile of other discarded toys. A feeling of lightness, like the first warm breeze of spring, washed over her.

She picked up the bear, his button eyes seeming to look up at her with unspoken understanding. A sense of gratitude bubbled up inside her, pushing away the gloom.

She paid for the bear, then, on a whim, also bought a small bouquet of wildflowers from another table. She left the sale with a skip in her step, the world suddenly painted in brighter hues.

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