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 old house felt different today, filled with memories of the past. Michael, sorting through boxes, felt a sense of melancholy. He'd found a collection of old books that belonged to his grandfather. He picked up a worn copy of "The Adventures of Sherlock Holmes" and opened it.

A single playing card, the Queen of Hearts, slipped out. A small, handwritten note was hidden behind it. A joke, a childhood memory, a private joke, it said. He smiled, a genuine smile, the first one he'd felt all day. A warmth spread through him, easing the ache in his heart. He felt a deep connection to his grandfather, a presence that filled the room. He felt no need for anything else.

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