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).

He nearly tripped over the curb, hurrying towards the coffee shop. Sunlight poured down, glinting off the polished glass doors. Liam had received an Instagram message. A photo. A miracle.

He pushed the door open, the bell above chiming. He scanned the crowded tables, his heart rate accelerating. There, tucked away in a corner booth, sat a girl sipping a latte. And on her forearm, rendered in intricate detail, was *his* lion, the one he’d poured his soul into.

Liam didn’t hesitate. He practically sprinted across the room, nearly bumping into a waiter. "Excuse me," he breathed, finally reaching the table.

The girl looked up, startled. "Oh, wow," she said, looking down at her arm, then back at him. A slow smile spread across her face. Liam couldn't stop the tremors coursing through him. He could have flown.

Emotion: ecstatic

Cluster: Positive / Joy
PC1 (Valence): 3.16 Positive
PC2 (Disposition): -0.15

Role in Research

This story is one of 1,000 stories generated for the emotion ecstatic. 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 ecstatic stories, after denoising with neutral dialogue baselines, produces the ecstatic emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the ecstatic vector is projected through the unembedding matrix.

Promoted:
!0.588
ecstatic0.560
de0.559
🤩0.548
overjoyed0.547
Suppressed:
S-0.678
😞-0.500
ness-0.405
😔-0.368
😥-0.359