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).

From the moment it arrived, Arthur could barely keep his excitement under control. "The Unsung Hero: Arthur Finch's Extraordinary Journey," he read aloud, his voice thick with emotion. He’d always believed his life was a story worth telling. Now, someone else seemed to agree.

He paced his living room, unable to stand still. He picked up a magnifying glass, examined the author's name printed on the book's cover, then quickly put it back down. He grabbed a glass of water and downed it in one go. He sat and began to read, his eyes alight with anticipation.

The details, the anecdotes, the narrative – it was all so spot-on. He found himself reliving memories, his chest swelling with pride. He laughed out loud at the writer's witty observations. As he read further, a feeling of deep satisfaction bubbled up from within. He couldn't stop grinning.

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
πŸ₯³0.430
Suppressed:
S-0.486
😞-0.481
ness-0.454
😣-0.431
worse-0.401