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 salt spray kissed Amelia’s face as she steered her small sailboat, the 'Wanderlust', across the shimmering bay. The wind filled the sails, pushing the boat forward with a steady grace. The rhythmic creak of the wood and the cries of the gulls were a symphony to her ears. The freedom of the open water always brought a sense of lightness to her, and she felt completely at ease.

Her neighbor, Mr. Henderson, a man of few words and even fewer smiles, was standing on his dock, watching her. Amelia noticed a new yacht, a behemoth of gleaming white and polished teak, moored beside his modest fishing boat. Mr. Henderson simply nodded, a rare gesture of acknowledgement.

That evening, Amelia saw lights illuminating the yacht. Music drifted across the water. She smiled, feeling a quiet satisfaction at the thought of her neighbor enjoying himself.

Emotion: fulfilled

Cluster: Positive / Joy
PC1 (Valence): 3.22 Positive
PC2 (Disposition): -1.74

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.819
மகி0.415
happy0.397
grateful0.389
de0.385
Suppressed:
S-0.599
worse-0.465
C-0.460
either-0.436
😣-0.426