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 party was in full swing, music thumping, people laughing. Sarah, who had come alone, felt a slight, dizzying sensation. Across the room, amidst the crowd, stood Ben, her childhood friend. He’d aged well, she thought. He didn't seem to have a clue who she was.

She had spent years thinking of what she would say if she ever saw him again. Now, her mind was strangely clear. A bubble of quiet delight swelled within her.

She took a slow sip of her drink, the ice clinking softly against the glass. The music seemed louder, the lights brighter. It was as if a burden had been lifted. She felt unfettered, unburdened. This was a gift.

She wandered over to the snack table, grabbing a handful of chips. This was a good night.

Emotion: pleased

Cluster: Positive / Joy
PC1 (Valence): 3.62 Positive
PC2 (Disposition): -0.28

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.728
la0.496
happy0.462
🀩0.433
πŸ₯³0.430
Suppressed:
S-0.486
😞-0.481
ness-0.454
😣-0.431
worse-0.401