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 afternoon sun streamed into the living room, illuminating the dust motes dancing in the air. Sarah sat on the couch, the laptop balanced precariously on her knees. A small, self-satisfied grin played on her lips. She had discovered the manuscript hidden under the bed, a well-kept secret.

The story was about her, a successful lawyer, and her somewhat clumsy, but always loving, husband. She saw herself in the character's determination, her wit, and her hidden vulnerabilities. The hero, Mark, was portrayed as a quirky, kind-hearted musician, very much like the real Mark.

She chuckled, a genuine sound of amusement and delight. The story was well-written, funny, and deeply affectionate. She found herself completely engrossed. This was a wonderful thing, a treasure he had kept hidden, all for her.

She closed the laptop, a light feeling in her limbs, and got up. She had some plans to make.

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
🥳0.430
Suppressed:
S-0.486
😞-0.481
ness-0.454
😣-0.431
worse-0.401