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 pounding bass still echoed faintly, even after Liam turned down the music. He stretched, a grin splitting his face. The complaint from Mrs. Gable, delivered in her usual brittle voice, hadn't completely soured his mood. He'd been celebrating his promotion, and a little neighborly displeasure seemed a small price.

He pictured the cake his colleagues had brought, the celebratory cheers, the genuine camaraderie he felt. A warmth bloomed in his chest. He made a mental note to bake Mrs. Gable some cookies tomorrow, maybe a simple apology on a note attached.

Liam went back to cleaning up the remnants of the party, whistling a jaunty tune. He felt... buoyant, like a balloon slowly rising in the air. The thought of the cookies, the chance to mend fences, made him smile again.

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