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 gentle rocking of the hammock in the garden lulled Ben into a tranquil state. He closed his eyes, the warmth of the sun on his face a balm to his soul. A gentle breeze rustled the leaves, creating a soothing melody. His life, a simple one of growing vegetables, was just as he wanted it.

His friend, Liam, always regaled him with stories of his glamorous life as a celebrity photographer. The world was at his fingertips. Ben listened, trying to hide the pangs of envy.

Then, he spotted Liam, not at a red-carpet event, but volunteering at the local animal shelter. The sensation that bloomed within him was one of pure, unadulterated happiness.

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