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).

"We are so terribly sorry, Mr. Chen." The advisor’s voice was filled with a contrite tone. The scholarship, his avenue to escape a future of manual labor, was not his. A clerical error, a misfiled application. The air in the office suddenly felt thick, oppressive.

Mark Chen held his breath. He had been planning his future, a future built on this scholarship. He felt the familiar weight of dread settling in his stomach, a crushing pressure. He was ready to fight.

Then, the advisor spoke again. They would honor his scholarship. A gasp escaped Mark's lips. The world tilted slightly. He had braced himself for a rejection, a denial, a return to the grind. Now, he felt as if he was walking on air. He thanked the advisor, and left with a newfound sense of purpose.

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