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).

"Okay, so this is the part where you…" Emily trailed off, re-explaining the process for the fifth time. She watched Alex, her soon-to-be replacement, with a gentle expression. She hadn’t expected this.

He had a way of looking at her that made her feel… warm. He was quiet, but attentive, his brow furrowed in concentration. The office felt warmer than usual today. The sun seemed to be shining just for them.

Each time he asked a question, she found herself explaining with extra care, as if each syllable was precious. His smile was infectious, and she found herself smiling back, a feeling she hadn't experienced in the office in ages. She wanted him to succeed, to understand, and to excel.

"That’s it," she said, her voice soft as she praised his progress. "You've got it."

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