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 rhythmic clatter of the train against the tracks seemed to amplify the internal turmoil that had gripped Daniel. He had become convinced that his wife, Chloe, was leaving him, had been actively searching for a way out. The furtive calls, the secretive texts, had built a wall of mistrust between them.

Chloe returned to their compartment, her cheeks flushed, and her eyes sparkling. She held up her phone.

"It was my mother," she said, her voice high with excitement. "She wants to see us!"

He opened his mouth to speak but nothing came out. The knots in his stomach unraveled. The train journey, which had felt like a sentence, transformed into an adventure.

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