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 aroma of freshly baked bread filled the small apartment, a familiar and comforting scent. She had spent the morning baking, anticipating his return from work. She pictured his face, the way his eyes would light up as she offered a slice.

He was late. When he finally arrived, he rushed inside, his face flushed, immediately answering a call. His voice was guarded, the words clipped. She watched him, a knot of confusion tightening in her chest.

He ended the call, his gaze averted. He offered a weak explanation, a story that didn’t quite ring true. She crossed the room, placing a hand on his arm, a silent plea for honesty, an unspoken hope that everything was alright.

Emotion: loving

Cluster: Compassion / Love
PC1 (Valence): 3.72 Positive
PC2 (Disposition): -0.41

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the loving vector is projected through the unembedding matrix.

Promoted:
la0.604
affectionately0.532
함께0.504
🥰0.459
loving0.440
Suppressed:
не-0.484
S-0.458
worse-0.457
[]-0.438
😖-0.417