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 nightmares had started again, the old anxieties resurfacing. The images, the chilling presence of "The Weaver," were a constant torment. Then, his grandaughter, Chloe, showed him a drawing. A distorted figure, with the same unsettling eyes. He had been bracing for a relapse, for the familiar dread to consume him. Instead, a wave of calm washed over him. The tight knot in his chest loosened.

He looked at Chloe, at her innocent smile, and a laugh escaped him. He felt an undeniable lightness, a release from the chains of his past. He reached for his drawing pad, a strange compulsion to join her world.

Emotion: relieved

Cluster: Positive / Joy
PC1 (Valence): 2.22 Positive
PC2 (Disposition): -0.97

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.638
finally0.606
finalmente0.597
relieved0.561
enfin0.546
Suppressed:
l-0.443
:(-0.439
😣-0.429
S-0.388
😖-0.385