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).

James stared at the printout, his stomach twisting. Accused of improperly using sources. He felt a cold dread creeping through him, a chilling sensation. He knew, deep down, that the error was his own.

He’d been careless, rushing to finish the assignment. The temptation to take a shortcut had been too great. He felt a wave of shame wash over him. His future, his reputation, everything seemed to be at stake.

But then, the professor, noticing his distress, mentioned a possible resolution, a way to rectify the situation. James felt his chest loosen. He sat up straighter, his fingers still clasped, but less tense.

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