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 room seemed to expand, the air filling her lungs as if she had just surfaced from a deep dive. For weeks, Amy had been anticipating a devastating truth bomb from Ben. He claimed to be a renowned astrophysicist, and the pressure of that grand lie had been suffocating. Observing him now, enthusiastically presenting a poorly-made robot to a group of children at the local library, a tide of ease washed over her.

She approached him with a genuine smile. "Ben! Are you putting on a show?"

Benโ€™s face went white. Then, a slow grin spread across his features.

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
๐Ÿ˜ฃ-0.429
S-0.388
๐Ÿ˜–-0.385