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 linseed oil and turpentine always calmed Eleanor. It was a sensory hug, a familiar comfort. For twenty years, she’d dedicated every spare moment to painting, the vibrant colors a language she used to speak to the world. Now, watching her daughter, Lily, meticulously blend a crimson hue on her own tiny canvas, a warmth bloomed in Eleanor’s chest. A genuine smile tugged at her lips as she leaned in to offer a tip, the shared passion a silent bond between them.

She watched Lily’s concentration, the tip of her tongue peeking out as she carefully applied the paint. It was like looking in a mirror, a younger version of herself, completely lost in the creative process. Eleanor reached for her own brush, a quiet contentment settling over her.

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