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).

John stared at the departure board, the numbers shifting and rearranging with each passing minute. The news of the late departure was met with a secret, silent sigh of ease. He was supposed to be at his ex-wife's wedding. He felt a soft buzzing sensation in his temples. He imagined the scene: the forced joviality, the inevitable small talk with distant relatives.

He leaned back, closing his eyes, the sterile airport air suddenly feeling…clean. His stomach muscles relaxed. He took a deep, deliberate breath, and a soft sound escaped his lips. Instead of rushing to pack his luggage, he went to buy a coffee, and a book he'd been meaning to start.

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