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 scent of freshly cut grass mingled with the aroma of barbecue as she surveyed her backyard. A gentle breeze rustled through the trees. After watching Mrs. Peterson discreetly pay for the landscaper, realizing the true nature of her neighbor’s wealth (the Peterson's garden!), a sense of optimism permeated through her.

She stretched, feeling the sun warm her skin. The worries that had plagued her earlier that week seemed to have vanished. She felt a lightness in her chest, a sense of peace that had been missing for a long time.

She picked up her drink and strolled over to the grill, ready for the evening. Her world felt changed.

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
😣-0.510
worse-0.477
😖-0.453