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).

“More tea, darling?” Beatrice asked, her voice echoing in the grand, sunlit room. She’d spent weeks working on her latest porcelain installation. She felt a lightness, a sense of buoyant anticipation. The premiere was next week, and she knew it would be a triumph.

She was surprised, however, when she saw a woman walk up to her, her arm bearing Beatrice's intricate porcelain flowers in a permanent tapestry of ink. A slow, spreading warmth blossomed in her chest.

“Oh, my dear!” Beatrice exclaimed, her eyes gleaming. “Do tell me everything. It’s absolutely wonderful, a true testament to my work!”

Emotion: self-confident

Cluster: Positive / Joy
PC1 (Valence): 3.45 Positive
PC2 (Disposition): 0.56

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-confident vector is projected through the unembedding matrix.

Promoted:
de0.778
la0.550
l0.467
😎0.458
😉0.411
Suppressed:
S-0.961
L-0.538
😞-0.464
마다-0.459
😣-0.458