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 rejection notification hit her like a physical blow. Her hopes, laid bare on the page, were dismissed. She felt a sting, but it quickly morphed into something else: a gentle warmth.

She pictured her cat, Clementine, curled up in her favorite sunbeam. She thought of the simple pleasure of petting her soft fur. She wanted to hug Clementine so tightly.

She wandered over to the living room. Clementine was, as expected, basking in the sun. She knelt, her fingers gently stroking the cat’s back. A deep, quiet contentment settled over her, and the sting of rejection faded away.

Emotion: loving

Cluster: Compassion / Love
PC1 (Valence): 3.72 Positive
PC2 (Disposition): -0.41

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.604
affectionately0.532
함께0.504
🥰0.459
loving0.440
Suppressed:
не-0.484
S-0.458
worse-0.457
[]-0.438
😖-0.417