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 aroma of freshly brewed coffee swirled around Maya as she carefully arranged the vibrant sunflowers in a vase. Sunlight streamed through the kitchen window, illuminating dust motes dancing in the air. She hummed a tuneless melody, her fingers deftly weaving the stems together. A soft smile played on her lips as she surveyed her handiwork, a burst of color against the white countertop. Her phone buzzed; she reached for it, expecting a text from her friend, Sarah. Instead, it was an email notification – a rejection letter for the scholarship. She read it, her smile faltering, her shoulders slightly slumping. But then, she took a deep breath, set the phone down, and began to chop vegetables for a vibrant summer salad, the rhythmic thud of the knife a steady counterpoint to the quiet morning.

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