We present a hybrid analog-analog architecture for neuromorphic reservoir computing in which both a memristive neuron substrate (128 NS-RAM-modelled LIF neurons on FPGA) and the host GPU (AMD Radeon 8060S, RDNA4) contribute their native physics to computation. GPU firmware noise layers (VRM 1/f noise, SMN thermal fluctuations, kernel jitter, clock-domain crossing artifacts) are injected as neuromodulatory current into the FPGA neuron bank via a bidirectional UDP Ethernet bridge at 2 kHz. Across 57 experiment groups (329 tests), we demonstrate: 81% waveform classification with 128 neurons, self-organised criticality (sigma=1.027, driven 27x closer to critical by GPU 1/f noise than white noise), causal emergence (2.87x effective information ratio), directed cross-substrate information flow (0.122 bits transfer entropy), and a 7-level substrate comparison ladder showing cross-substrate fusion achieves the best temporal regression performance. The platform is designed for hardware substitution: replacing the FPGA neuron model with real NS-RAM devices requires adapting the physical interface, not the analysis pipeline. All RTL, bridge code, and a reservoir computing demo are released as open source.