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 sunlight was warm on Clara’s face as she scrolled through the blog post. Her mouth had a tight, almost painful curve. The headline blared, "Echoes of Genius: Uncovering the Inspirations of Alistair Finch." Underneath, her story was quoted and the similarities to Finch’s latest novel were laid bare.

She stretched, her back cracking in a satisfying way. She reached for the cup of coffee she had made. It now felt the best coffee she had ever had. The bitterness of the dark roast was a perfect counterpoint to the sweetness of the unfolding revelation.

"Well, well, well," she murmured, a soft laugh bubbling up from her chest. The world suddenly seemed brighter, more vibrant.

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