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 sterile white walls of Dr. Ramirez’s office seemed brighter, almost cheerful, after the news. I leaned back in my chair, a wide grin plastered across my face. He had the same condition. He *understood*.

"So," I began, my voice brimming with an excitement I couldn't contain. “The muscle fatigue? The spatial disorientation? The… the craving for certain foods that somehow *work*?” My hands flew about as I described the symptoms.

Dr. Ramirez, a man usually stoic, simply nodded in agreement. His eyebrows were raised, mirroring the enthusiasm on my face. A shared glance, a bond forged in a rare affliction.

Emotion: delighted

Cluster: Positive / Joy
PC1 (Valence): 3.80 Positive
PC2 (Disposition): -0.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.611
🤩0.536
de0.530
ecstatic0.527
🎉0.524
Suppressed:
S-0.687
😞-0.562
ness-0.471
😔-0.385
😥-0.379