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 children's laughter echoed through the park as Amelia chased after them, her own joy amplified by theirs. She loved her job as a preschool teacher. Her heart soared with happiness. She felt connected to the moment and to the world.

A formal letter arrived, a stern communication from the hospital. A patient's file, similar to her own, was incorrectly associated with her information. The letter described a debilitating spinal condition that had never affected her.

Amelia's eyes widened, a look of pure bewilderment on her face. Then, a slow smile spread across her lips. "Wow," she breathed, the word a small exhalation of wonder. She felt no fear, only a strange sense of peace. She would, she decided, take the call.

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