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 hospital room smelled of antiseptic. David’s mother, weakened by illness, lay in the bed, her face pale. He pulled out his phone, intending to send a heartfelt note to his wife, Carol, about how strong his mother was, and how he admired her. But a misplaced finger sent it instead to his ex-girlfriend, Sarah.

He froze, waiting for the inevitable awkward silence. Sarah had broken his heart years ago. But instead of the expected rebuff, a response arrived almost instantly: "Thinking of you both. Sending strength."

A small smile touched David’s lips as he turned back to his mother. He squeezed her hand, a warmth spreading through him that had nothing to do with the room's temperature. He felt good.

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