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).

He practically vibrated in the waiting room, pacing back and forth. The past few weeks had been a blur of research, of whispers, of anticipation. Now, the moment of truth.

The nurse called his name, and he practically sprinted to the examination room. The doctor, a woman with a no-nonsense air, was already there, flipping through a file.

"Mr. Davis," she said, her voice flat. "We have an issue."

He could barely keep the grin off his face. "A mix-up?" he squeaked, his voice cracking with the strain of holding back his… glee.

The doctor looked up. "Indeed. Your records... belong to Mr. Smith. And his, to you."

He let out a whoop of pure, unadulterated joy, clapping his hands together with unrestrained happiness. "Magnificent! Absolutely magnificent!"

Emotion: excited

Cluster: Positive / Joy
PC1 (Valence): 3.21 Positive
PC2 (Disposition): -0.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.809
!0.564
excitedly0.500
🀩0.491
!"0.466
Suppressed:
S-0.721
ness-0.519
😞-0.424
grieve-0.310
πŸ˜”-0.300