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 old carousel, with its painted horses and twinkling lights, brought a smile to Kevin's face. He felt at ease, calm, and… complete.

“Remember our first date, Sarah? At this place?” Kevin said, his gaze fixed on the spinning horses.

Sarah tilted her head. "Yes, I do. We were 14, and you were too scared to touch my hand."

Kevin chuckled. "I think I held your hand, though. I remember we spent hours talking about our dreams."

Sarah smiled gently. “Kevin, we met on a class trip. We barely spoke. I think you're confusing me with someone else.”

Kevin’s face fell. He replayed the memory in his mind, but the details became blurry.

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