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).

Rain lashed against the windows of the small apartment, mirroring the turmoil in David’s stomach. He hadn't eaten properly in days, and the eviction notice sat on his kitchen table, a stark reminder of his dwindling funds. He was kicking a loose stone down the street, head hung low, when his foot bumped into something hard. A wallet. Inside, a staggering amount of cash.

He stared at the money, the weight of it in his hands a curious sensation. He knew, instinctively, who it belonged to - the elderly woman from the apartment complex with the kind smile and the ailing cat. He found her address with the help of a local directory, and hurried to her door, his pace almost frantic. Seeing her face light up, he felt a lightness he couldn't explain. "Oh, you are an angel," she murmured, clutching the wallet to her chest.

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