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 tiny sailboat bobbed gently on the harbor. David felt the warm sun on his face, a pleasant contrast to the cool sea breeze. He traced his finger down the list. Item number three: "Sail around the Greek Islands." He’d managed to find a small boat and booked a flight for next week.

The boat was simple, just a few sails and a small cabin, but it was perfect. The clear water beckoned. He'd never sailed before, but he was eager to learn. A flush of heat warmed his cheeks.

He pictured himself exploring hidden coves, enjoying the simple pleasures of the sea. It was a daunting task, but he couldn't wait.

Emotion: optimistic

Cluster: Positive / Joy
PC1 (Valence): 4.44 Positive
PC2 (Disposition): -0.49

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.856
la0.688
!0.601
enthusi0.530
🀩0.515
Suppressed:
S-0.891
😞-0.504
L-0.486
ness-0.478
γγ‚Œγ§γ‚‚-0.432