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 knock on the door was hesitant. Liam peered through the peephole to see old Mr. Peterson, clutching a watering can. He braced himself, expecting a fight about the noisy lawnmower again. However, all Mr. Peterson wanted was to plant some root vegetables near the fence.

Liam, without a second thought, readily agreed. The relief was instantaneous, washing over him in a wave of warmth. He felt his jaw unclench, the muscles suddenly loose. The weight on his chest disappeared as if it never existed. He grinned; the prospect of not having to manicure that section of lawn anymore brought a strange sense of joy.

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