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 the air, mingling with the scent of old books. John leaned back in his chair, a small smile playing on his lips. His son, Ethan, had been keeping a secret, a large one, apparently. John had found the account a few hours ago.

He felt the corners of his mouth lift further. He felt a rush of something – a peacefulness, perhaps? – as he reread the posts. His son was deeply creative, something he had always suspected but hadn't confirmed.

He looked forward to the future, to getting to know his son in a new way, to sharing his life. He pictured the future with a newfound eagerness. He felt ready to embrace this new chapter.

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